Research

New papers ranked by attention, with their code, models and discussion linked. Pick a field on the left.

Week Month Quarter All

Newest Most relevant

Papers

Research

New papers ranked by attention, with their code, models and discussion linked. Pick a field on the left.

Week Month Quarter All

Newest Most relevant

Papers

arXiv cs.AIOct 12
Structural Baselines Matter for Agent Failure Detection and Attribution
Ramesh Arvind Naagarajan, Stefan Streif
An LLM agent using tools can fail silently. It stops before the task is done, raises no error, and answers fluently. Two kinds of monitor address this, one deciding whether a run failed and the other naming the step where failure became unavoidable. Much of the reported performance on both tasks comes from regularities that need no model. Failing runs are longer, and the step labelled decisive is usually the last. A rule that always names the last step is correct $67\%$ to $96\%$ of the time here, without reading the run at all. That ceiling reflects how the labels were written, not how agents break. On failures whose decisive step replay can confirm, it falls to near chance. Reporting gain over that rule therefore changes what a score means. Under that correction, methods tested here gain nothing on give-up failures, while several published systems keep a clear advantage on other splits. For detection, the agent's internal states beat transcript length and text similarity on the agent benchmark, and hold up where the text baseline does not. Precision stays low when failures are rare, so such a monitor should rank runs for review, not replace it.
PDF
arXiv cs.LGOct 12
Compression Through Time: An Interplay of Separability, Stationarity and Capacity
Nikolaus Kopp, Franz Pernkopf, Bernhard Geiger
Information-theoretic and geometric compression have been widely studied as possible explanations for generalization. Yet their temporal dynamics in recurrent networks remain largely unexplored. Using discretized LSTMs, whose finite embedding space enables direct estimates of information quantities, we observe pronounced compression across the final timesteps of many datasets. We explain this effect through three competing mechanisms: (i) class separability permits stronger compression at the final timestep; (ii) shared recurrent dynamics propagate this pressure across timesteps with similar activation states, making its extent depend on temporal stationarity; and (iii) limited representational capacity opposes prolonged compression because it restricts information available for subsequent computation. We systematically test these mechanisms through controlled synthetic interventions and real-world sequence tasks. Our results identify class separability, temporal stationarity, and network capacity as key determinants of temporal compression, and suggest that compression acts as a regularizer-potentially beneficial when excess capacity is available, but harmful to generalization…
PDF
arXiv eess.SPOct 12
RFWeave: Learning Wireless Propagation Across Scenes and Transceiver Configurations
Shurui Xu, Xiao Ye, Yijie Bian, Junjie Ai, Yuxuan Chen +3
Wireless propagation modeling is foundational to the evaluation and design of modern communication systems. To achieve accurate wireless propagation prediction, recent learning-based approaches leverage scene geometry and materials, demonstrating promising generalization across transceiver locations and unseen scenes. However, these approaches remain largely confined to a fixed configuration of array size, receiver orientation, and transmit beam. In this work, we introduce RFWeave, a learned wireless propagation model designed to generalize across scenes, transceiver locations, and transceiver configurations. To accommodate varying array structures, RFWeave incorporates variable-length transceiver tokens that represent antenna elements individually. Furthermore, to capture the geometry between transmit and receive antenna elements, RFWeave aggregates their pairwise spatial relations into propagation tokens. A configuration-conditioned decoder predicts the spatial spectrum and received power. RFWeave is trained on a large-scale simulated dataset spanning 10,000 indoor scenes and more than 5 million channel records under diverse transceiver configurations. Extensive evaluations…
PDF
arXiv cs.AIOct 12
Does a Hosted Decision Model Respect Irrelevant Alternatives? A Pre-Registered Test of Option-Set Dependence in Jev
Dushyant Rajput, Nirdesh Chauhan, Siddharth Kosaraju
Decision APIs that return a probability for each option are routinely used as if those probabilities were properties of the options themselves. That reading is valid only if the model satisfies independence of irrelevant alternatives (IIA): adding an option that is neither the right answer nor its strongest rival should leave the odds between those two unchanged. We test this in a pre-registered study of jev-1.13.0, a hosted decision model, using 299,463 calls on intent classification (BANKING77, CLINC150) and topic classification (AG News). Every added option moves the log-odds between the gold label and the strongest wrong label: the root-mean-square systematic shift is 0.20-0.52 nats, 1.2 to 3 times the run-to-run variation, even when the added option takes at most 0.1% of the probability mass. The shifts are directional. An option similar to the wrong answer draws probability from it (+0.10 nats toward the gold label). A paraphrase of the wrong answer produces an intermediate pattern: the gold label's probability is almost conserved, but the paraphrase receives only about a third of the wrong answer's share rather than the half that strict substitution implies. The distortion…
PDF
arXiv cs.LGOct 12
Guidance Without Labels: Flow Matching from Coupled Gaussian Mixtures
Stanislas Ducotterd, Bassam El Rawas, Michael Unser
Flow matching models are typically trained to transport a Gaussian source to the data distribution, with source and target samples paired independently. We replace the source with a fitted Gaussian mixture and couple each data point to a mixture component through an entropic optimal transport problem. We show that the resulting transport reduces to the standard Gaussian-source problem up to a guidance-like correction, which enables the reuse of a pretrained velocity field. This correction is a closed-form function of the fitted mixture plus a term that we learn with a small correction network. We test our model on published checkpoints for CIFAR-10 and CelebA-HQ. It improves FID at every step count, and on CelebA-HQ it reaches the quality of the baseline with about half the steps. The closed-form term alone, with no training, already delivers most of this improvement; the small correction network accounts for the rest.
PDF
arXiv cs.LGOct 12
Counting with Attention and LayerNorm: Norm Scaling and Representation Geometry
Ayyub Shaffy, Manoj Dhakal, Safal Shrestha, Keith W. Ross
Counting is a simple task on which transformers can nevertheless fail at long sequence lengths. We study the cost of counting in a single attention layer, up to a maximum length $L$, focusing on how softmax attention and layer normalization shape the representation from which the count is recovered. We mainly focus on regression read-out but also consider classification read-out. For regression, we show unnormalized linear attention counts exactly at parameter norms independent of $L$. For softmax attention, regression cannot count exactly with finite parameters; it recovers the count after rounding, but only when the vector parameter norms grow with $L$. We measure this cost by $B_{\min}$, the smallest bound that can be placed on every trainable vector to ensure exact counting after rounding, and derive tight rates. At fixed model dimension, $B_{\min}$ grows as $L$ without normalization, as $L^{3/2}$ under bare post-normalization, and as $L^{3/4}$ with learned post-normalization. The last rate is unexpected: post-normalization discards the magnitude that carries the count and might be expected to make counting harder, yet with a learnable gain it counts at a smaller norm than…
PDF
arXiv cs.LGOct 12
IND-Eval: Aligning Evaluation and Simulation for Industrial Time Series Foundation Models
Vebjørn Haugland, Pavel Gulin, David Foss, Peet Cremer, Erlend Aune +3
We introduce IND-Eval, a public benchmark that organizes industrial time series across domains into source-specific forecasting tasks. Relative to established benchmarks such as GIFT-Eval, it emphasizes finer sampling resolutions and a greater prevalence of multivariate forecasting. Evaluating Chronos-2, TiRex-2, and TimesFM-3, we find that TimesFM-3 achieves the lowest source-balanced aggregate nMASE and nCRPS and leads seven of nine sources under each metric; source-specific exceptions reinforce the need for domain-representative evaluation for model selection. These findings also motivate improving domain alignment during pretraining, where real industrial data are often too scarce to close domain-specific gaps directly; we therefore investigate whether a domain's statistical structure can guide simulator design. In a case study on two offshore well-monitoring regimes, we improve a general simulator's coverage using an oscillator-augmented simulation pipeline. This lowers forecasting error in the target domain but reduces performance on the subset of GIFT-Eval with natively univariate targets. A 50/50 mixture of the general and augmented simulation recipes achieves the lowest…
PDF
arXiv cs.CLOct 12
SIREN: Situation-aware Index for Response and Emergency ActioNability in Crisis Translation
Maria Carmen Staiano, Lifeng Han, Johanna Monti, Francesca Chiusaroli
Machine translation (MT) is increasingly utilized in multilingual crisis communication, yet conventional evaluation does not directly assess whether translated emergency messages preserve their actionability. We introduce SIREN (Situation-aware Index for Response and Emergency ActioNability), a human evaluation framework assessing whether translation choices compromise protective action, directive force, and urgency of the source text. We evaluate SIREN in two complementary settings. At the error level, we apply it to HOPE-annotated Italian--English translations produced by ChatGPT-4o and Google Translate: 31.63\% and 48.73\% of errors, respectively, compromise actionability, predominantly by affecting the protective action. At the message level, we evaluate English--French translations produced by TranslateGemma-4B and Google Translate, with actionability preserved in 85.34\% and 92.67\% of translations, respectively. TranslateGemma-4B failures predominantly weaken directive force, whereas Google Translate failures more often compromise protective actions and receive Major impact ratings. These findings show that translation systems can differ not only in how often actionability…
PDF
arXiv cs.LGOct 12
Learning Incompressible 3D Flows from Sparse Samples: A Set Transformer Approach to Divergence-Free Kernel Fitting
Ramzi Idoughi, Radouan Boukharfane, Peter Wonka
Recovering divergence-free velocity fields from sparse and corrupted observations requires reconciling physical consistency, expressive representations, and robustness to missing data. We introduce DFK-Former, a set-to-field transformer that reconstructs divergence-free velocity fields from sparse, noisy, and irregularly sampled 3D observations. The model is inherently invariant to the number and ordering of input samples and predicts the parameters of a divergence-free kernel representation, producing continuous, mesh-free velocity fields that satisfy incompressibility exactly by construction rather than approximately through soft constraints or projection operators. Unlike existing divergence-free kernel approaches, which estimate kernel coefficients via a separate optimization for each field, DFK-Former predicts these coefficients directly in a single forward pass. This eliminates costly iterative fitting while providing a learned prior that enables accurate reconstruction even when observations are insufficient to uniquely determine the field. To enhance representational power, we introduce adaptive and anisotropic divergence-free kernels that preserve exact incompressibility…
PDF
arXiv cs.LGOct 12
Learning Deployable Causal Action Geometry under Temporal Non-Stationarity
Changjian Liu, Tianyu Wang, Yuwei Xu, Xiaoxuan Deng, Zhilin Zhang +4
Learning a response law for continuous decisions from observational time series is central to many real-world decision systems, yet temporal non-stationarity poses a fundamental challenge: as outcomes drift over time, naively pooled models can conflate action effects with shifting baselines and even reverse action rankings. Even when the one-step response is identifiable, unrestricted cross-time generalization remains fundamentally ill-posed. We therefore seek the part of the response that remains stable for decisions even when outcome levels do not. We propose deployable causal action geometry: the action-response shape that remains after anchoring away action-independent level shifts on a selected link scale and profiling out positive amplitude variation. Building on this target, we develop a two-stage orthogonal estimator that first obtains cross-fitted pilot estimates of anchored responses and then performs honest profiled selection over link, representation, and shape classes. The resulting estimator admits oracle guarantees for the restricted target and, under approximate persistence, produces decision rules that remain near optimal in future periods. Experiments on…
PDF
arXiv cs.CLOct 12
SuPER-Mamba: Surprisal Prioritization for Extended-Context Routing in Mamba
Zhetong Zhang, Gayan K Kulatilleke
State space models provide efficient linear-complexity processing for long sequences, but their performance frequently degrades as context length grows. We propose SuPER-Mamba, a training-free framework that uses Surprisal as a model-intrinsic signal for long-range state routing in pretrained Mamba models. SuPER-Mamba computes position-wise Surprisal from next-token predictions, aggregates neighboring responses through Local Pooling, and uses the resulting scores to prioritize Global-Channel updates without query-dependent scoring or additional training. We evaluate SuPER-Mamba on three state-space models across the LongBench-E benchmark. The results show that SuPER-Mamba improves the average score from 8.06 to 15.69, corresponding to a 94.7% relative gain over the Base Models and a 13.1% improvement over the state-of-the-art prior baseline. Ablation and length-wise analyses further support the effectiveness of the proposed routing framework.
PDF
arXiv cs.LGOct 12
ACED: Reference-Anchored Aggregation of Natural-Language and Executable Evidence for Mathematical Reasoning
Yiyi Lu, Jiaxiang Geng, Bing Luo
Natural-language self-consistency and executable programs provide complementary test-time evidence for mathematical reasoning, yet either channel may support the same semantic error. Thus we propose ACED, a reference-anchored framework that treats the self-consistency answer as the default and executable outputs as supporting evidence rather than interchangeable votes. ACED converts source-specific answer counts into smoothed supports, combines them through a weighted logarithmic pool, and overrides the reference only when a calibrated relative-evidence margin is exceeded. The same rule supports both candidate selection and admission of executable-only answers. Across five math word-problem benchmarks, ACED matches or outperforms the corresponding baselines. On GSM8K, ACED-CANDIDATE recovers 89.7% of the attainable candidate-set gain with only three damaging overrides, while ACED-ALL reaches 86.9% accuracy versus 82.6% for direct Program-of-Thought aggregation. These results show that preserving evidence provenance enables more reliable integration of natural-language and executable reasoning.
PDF
arXiv cs.ROOct 12
Language2Drive: Do Vision-Language-Action Models Really Follow the Instructions in Autonomous Driving?
Zihan You, Zehua Fan, Wenqi Lyu, Aoqi Wang, Ni Wang +17
Recent Vision-Language-Action (VLA) models increasingly use natural-language instructions to condition autonomous driving behavior. Yet existing closed-loop benchmarks primarily measure route completion, safety, and rule compliance, leaving a fundamental question unresolved: does language actually determine which feasible behavior the vehicle executes? A trajectory may be safe and successful while still violating or even ignoring the passenger's instruction. To address this, we introduce \ltd, a benchmark designed to directly test this capability. Its key evaluation unit, the paired counterfactual unit (PCU), holds the initial driving scene fixed while changing only the instruction. This design enables us to distinguish isolated instruction success from counterfactual paired success across four instruction-following scopes. To test whether this distinction persists across evaluation regimes, we instantiate Language2Drive in complementary closed-loop CARLA simulation, reconstructed real-world scenes, and open-loop driving benchmarks, including our released CARLA-Language2Drive simulator with purpose-built maps. Evaluating representative driving VLAs across these settings reveals a…
PDF
arXiv cs.CVOct 12
REEL: Learning to Retrieve, Evaluate, and Evolve Visual Memory for Any Long-Horizon Multi-Shot Video Generation
Hang Xu, Guohui Zhang, Xiaoxiao Ma, Hu Yu, Jie Huang +5
Memory-based long-video generation aims to combine user control with long-range visual consistency. We organize this process into three functional components: a planner, an adapter, and a generator. Representative multi-shot systems couple memory to generator-specific interfaces or use predefined agent workflows, rather than independently training a memory policy for cross-shot objectives. We introduce REEL, a general-purpose visual-memory planner. Through a unified tool interface, REEL learns to retrieve references, create missing visual evidence, and update persistent memory. Backend-specific adapters translate its evidence plans into supported conditioning inputs, allowing the same policy to guide different black-box video generators. To train REEL, we construct two high-quality datasets, REEL-SFT-4k and REEL-RL-1k, covering diverse interaction patterns and prompt types. Training proceeds in three stages: supervised fine-tuning, single-shot Group Relative Policy Optimization (GRPO), and multi-shot GRPO. Multi-shot GRPO carries policy-generated memory across consecutive shots, so later outcomes guide earlier reference selection and memory updates. REEL-Bench tests identity…
PDF
arXiv cs.LGOct 12
AeroChem: Closed-loop Physics-Informed State Space Modeling for Long-term Chemically-Reactive Air Quality Forecasting--Extended Version
Kien Le Trung, Tung Kieu, Dinh Duc Nha Nguyen, Cuong Do, Bin Yang +1
Accurate long-term air quality forecasting is challenging due to long-range transport, meteorological variability, and nonlinear chemical reactions underlying secondary pollutant formation. Purely data-driven models often suffer from long-horizon drift and lack physical consistency, while existing physics-informed approaches commonly follow open-loop designs that fuse neural and physical components only at the output level. We propose AeroChem, a closed-loop physics-informed state space framework for chemically reactive air quality forecasting. AeroChem adopts a two-branch co-correction design: a UDE-based process branch provides a structured but imperfect physical prior, while a Mamba-based virtual measurement branch captures long-range temporal context and produces probabilistic virtual observations. Neural Kalman Fusion couples the two branches by correcting the latent physical state at each forecasting step and feeding the posterior state back into the simulator, reducing long-horizon drift. We further introduce HanoiAir, a real-world dataset integrating pollutant concentrations, meteorology, and emission inventories. Experiments on HanoiAir and a public benchmark show that…
PDF
arXiv cs.HCOct 12
Integrating Feature Understandability into Feature Selection for Human-Centred Tabular Explanations
Nicola Rossberg, Bennett Kleinberg, Barry O'Sullivan, Luca Longo, Andrea Visentin
Existing human-centred XAI research predominantly evaluates explanations after they have been generated. However, this fails to provide actionable insights into improving accessibility. This study incorporates human-based feature understandability into feature selection to improve the generation of human-centred explanations. Natural language explanations for machine learning models trained on tabular data often cite influential features in the input data to explain a given decision. As a consequence, users' ability to understand the produced explanation hinges on their understanding of the cited features. To quantify this natural-language feature understandability, Rossberg et al. proposed the Feature Understandability Scale, which assigns numerical `understandability scores' to features based on user feedback. To evaluate the degree to which these scores can improve machine learning explanation quality, this study collects understandability scores across two datasets, proposes an understandability-aware feature selection algorithm to select features that are both understandable and informative, and trains a random forest based on these feature subsets. The SHAP-based…
PDF
arXiv cs.AIOct 12
LATCH: LLM-Assisted Timing Closure Harness for Post-Route FPGA Optimisation
Shu Gu, Matthew Youngman, Yuqin Zhao, Cristian Sestito, Ali Siddique +3
Post-route FPGA timing closure remains expert-dependent and computationally expensive. We present LATCH (LLM-Assisted Timing Closure Harness), a two-layer framework that separates large language model (LLM) orchestration from deterministic FPGA implementation and evaluation. Across sixteen designs and seven LLMs, a single-iteration study compares three agent control granularities - expert-written recipes, direct EDA operations and LLM-constructed procedures - to ask how much control an agent needs per attempt. Functional-pass rates are 98.2%, 71.4% and 17.9%, respectively; yet direct operations give slightly larger 3.4% median Fmax gains when passing, versus 3.2% for recipes. This exposes a trade-off between execution reliability and timing improvement. Informed by this trade-off, a multi-iteration study fixes the action tier at expert recipes to ask how repeated attempts are best organised, comparing a fitted deterministic heuristic with sequential LLM reasoning, branching exploration and knowledge base-guided exploration within 12 checkpoints per run. Branching raises mean maximum-frequency improvement from 10.5% (sequential) to 16.0%, and the knowledge base to 20.3%, improving…
PDF
arXiv cs.CVOct 12
Adaptive Interaction Network for Human Motion Prediction During Human-Robot Collaboration
Mengyuan Liu, Yangting Lin, Qiongjie Cui
Human motion prediction during human-robot collaboration is critical for achieving safe and efficient interactions in shared environments. Unlike previous studies that have primarily focused on humans and objects, we focus on the robot-aware human motion prediction task, which explicitly models the influence of robots on human motion. This task presents new challenges, such as capturing human-robot heterogeneity and modeling complex spatial interactions. To address these issues, we develop an adaptive interaction network (AINet) model that consists of two branches: a primary branch that predicts future human motion and an auxiliary branch that estimates robot trajectories. The two branches are jointly optimized and coupled via a Local-Global Spatial Interaction (LGSI) Module, which effectively captures fine-grained and global contextual dependencies between human and robot motion sequences. Then, we introduce an Adaptive Weighted Aggregation (AWA) Module to dynamically fuse motion features using context-dependent weights, thereby increasing adaptability across diverse scenarios. Furthermore, we adopt a coarse-to-fine prediction strategy, in which a coarse pseudo-trajectory is…
PDF
arXiv cs.CVOct 12
Answer It or Not? Towards Prompt-Adapted Adversarial Images on Vision Language Models
Shunyuan Bai, Yuchen Ren, Le Yang, Chenhao Lin, Chao Shen +1
With the advancement in language modeling, research on adversarial images has recently shifted from image classifiers to vision-language models (VLMs). Despite the new, text-prompt-driven nature of VLMs, we find that existing VLM adversaries have largely overlooked the dynamics of text prompts. In a typical use case, adversarial images can protect visual privacy by rejecting VLMs from answering questions about the image. However, existing protections are prompt-agnostic, i.e., indiscriminately rejecting any question, including those for potential legitimate use of the image. To address this limitation, we propose Prompt-Adapted (ProAda) adversarial images, which are optimized to balance the rejection of harmful prompts and the correct response of legitimate prompts. In particular, to achieve a more accurate adversarial direction, the text prompt is also iteratively updated with a simple classifier judging whether the harmfulness of the prompt remains. Extensive experiments on visual-privacy-related datasets validate that ProAda can reject over 90% of harmful prompts while allowing over 90% of legitimate ones, demonstrating superior overall performance compared to existing…
PDF
arXiv cs.AIOct 12
Weak Segmentation-Guided GAN for~Realistic Color Edition
Vincent Auriau, Emmanuel Malherbe, Matthieu Perrot
Editing the color of images in a realistic way finds many applications such as changing the perception of an image, data augmentation or film post processing. The design of an automatic tool is a complex and long addressed challenge. In particular, two properties are difficult to meet altogether: generating realistic results without artifacts and the possibility to precisely choose the future color. Conventional methods using segmentation and histogram matching maximize the controllability but also introduce a lack of realism or are complex to automate. On the contrary, GANs that specialize in realism are difficult to control. To overcome these challenges, we propose a novel GAN architecture leveraging any differentiable segmentation model. We demonstrate the genericness of our framework that presents state of the art results on different use cases. It generates images that look realistic while offering a precise color control.
PDF

Papers

Open problems across fields

Lack of benchmarks for agent harness reliability1 paper raises it · 1 addresses it
Existing benchmarks focus on model capabilities rather than the reliability of the systems that support agent operation.
- Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attributionraises · addresses
Unclear net value of agent memory1 paper raises it · 1 addresses it
Dedicated memory systems often underperform naive retrieval, making their benefits uncertain.
- Memory Tax: Dissecting the Net Value of Agent Memoryraises · addresses
Token collapse in graph soft prompting1 paper raises it · 0 address it
Graph-specific tokens become indistinguishable, failing to convey intended relational information.
- On the Token Collapse Phenomenon in Textual Graph Soft Promptingraises
Poor trajectory supervision for tool-use agents1 paper raises it · 1 addresses it
Successful trajectories may lack compositional coverage or decision grounding, limiting agent learning.
- Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agentsraises · addresses
Uneven evaluation of coupled agent-world model systems1 paper raises it · 1 addresses it
Separate evaluation of agents and world models fails to predict their joint performance or sustained learning.
- Dual Exam: Controlled Evaluation of Multimodal Agents and World Modelsraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Rising research topics

Channel state information14+40.0%
Anomaly detectors21+23.5%
AI tutors13+8.3%
Character recognition OCR10−9.1%
Multimodal emotion7−12.5%
Physics informed neural121−16.6%
Machine learned interatomic33−29.8%
Supervised & diffusion models80−30.4%

Rising research topics

Ask the research

Sample

Papers

arXiv cs.AIOct 12
Structural Baselines Matter for Agent Failure Detection and Attribution
Ramesh Arvind Naagarajan, Stefan Streif
An LLM agent using tools can fail silently. It stops before the task is done, raises no error, and answers fluently. Two kinds of monitor address this, one deciding whether a run failed and the other naming the step where failure became unavoidable. Much of the reported performance on both tasks comes from regularities that need no model. Failing runs are longer, and the step labelled decisive is usually the last. A rule that always names the last step is correct $67\%$ to $96\%$ of the time here, without reading the run at all. That ceiling reflects how the labels were written, not how agents break. On failures whose decisive step replay can confirm, it falls to near chance. Reporting gain over that rule therefore changes what a score means. Under that correction, methods tested here gain nothing on give-up failures, while several published systems keep a clear advantage on other splits. For detection, the agent's internal states beat transcript length and text similarity on the agent benchmark, and hold up where the text baseline does not. Precision stays low when failures are rare, so such a monitor should rank runs for review, not replace it.
PDF
arXiv cs.LGOct 12
Compression Through Time: An Interplay of Separability, Stationarity and Capacity
Nikolaus Kopp, Franz Pernkopf, Bernhard Geiger
Information-theoretic and geometric compression have been widely studied as possible explanations for generalization. Yet their temporal dynamics in recurrent networks remain largely unexplored. Using discretized LSTMs, whose finite embedding space enables direct estimates of information quantities, we observe pronounced compression across the final timesteps of many datasets. We explain this effect through three competing mechanisms: (i) class separability permits stronger compression at the final timestep; (ii) shared recurrent dynamics propagate this pressure across timesteps with similar activation states, making its extent depend on temporal stationarity; and (iii) limited representational capacity opposes prolonged compression because it restricts information available for subsequent computation. We systematically test these mechanisms through controlled synthetic interventions and real-world sequence tasks. Our results identify class separability, temporal stationarity, and network capacity as key determinants of temporal compression, and suggest that compression acts as a regularizer-potentially beneficial when excess capacity is available, but harmful to generalization…
PDF
arXiv eess.SPOct 12
RFWeave: Learning Wireless Propagation Across Scenes and Transceiver Configurations
Shurui Xu, Xiao Ye, Yijie Bian, Junjie Ai, Yuxuan Chen +3
Wireless propagation modeling is foundational to the evaluation and design of modern communication systems. To achieve accurate wireless propagation prediction, recent learning-based approaches leverage scene geometry and materials, demonstrating promising generalization across transceiver locations and unseen scenes. However, these approaches remain largely confined to a fixed configuration of array size, receiver orientation, and transmit beam. In this work, we introduce RFWeave, a learned wireless propagation model designed to generalize across scenes, transceiver locations, and transceiver configurations. To accommodate varying array structures, RFWeave incorporates variable-length transceiver tokens that represent antenna elements individually. Furthermore, to capture the geometry between transmit and receive antenna elements, RFWeave aggregates their pairwise spatial relations into propagation tokens. A configuration-conditioned decoder predicts the spatial spectrum and received power. RFWeave is trained on a large-scale simulated dataset spanning 10,000 indoor scenes and more than 5 million channel records under diverse transceiver configurations. Extensive evaluations…
PDF
arXiv cs.AIOct 12
Does a Hosted Decision Model Respect Irrelevant Alternatives? A Pre-Registered Test of Option-Set Dependence in Jev
Dushyant Rajput, Nirdesh Chauhan, Siddharth Kosaraju
Decision APIs that return a probability for each option are routinely used as if those probabilities were properties of the options themselves. That reading is valid only if the model satisfies independence of irrelevant alternatives (IIA): adding an option that is neither the right answer nor its strongest rival should leave the odds between those two unchanged. We test this in a pre-registered study of jev-1.13.0, a hosted decision model, using 299,463 calls on intent classification (BANKING77, CLINC150) and topic classification (AG News). Every added option moves the log-odds between the gold label and the strongest wrong label: the root-mean-square systematic shift is 0.20-0.52 nats, 1.2 to 3 times the run-to-run variation, even when the added option takes at most 0.1% of the probability mass. The shifts are directional. An option similar to the wrong answer draws probability from it (+0.10 nats toward the gold label). A paraphrase of the wrong answer produces an intermediate pattern: the gold label's probability is almost conserved, but the paraphrase receives only about a third of the wrong answer's share rather than the half that strict substitution implies. The distortion…
PDF
arXiv cs.LGOct 12
Guidance Without Labels: Flow Matching from Coupled Gaussian Mixtures
Stanislas Ducotterd, Bassam El Rawas, Michael Unser
Flow matching models are typically trained to transport a Gaussian source to the data distribution, with source and target samples paired independently. We replace the source with a fitted Gaussian mixture and couple each data point to a mixture component through an entropic optimal transport problem. We show that the resulting transport reduces to the standard Gaussian-source problem up to a guidance-like correction, which enables the reuse of a pretrained velocity field. This correction is a closed-form function of the fitted mixture plus a term that we learn with a small correction network. We test our model on published checkpoints for CIFAR-10 and CelebA-HQ. It improves FID at every step count, and on CelebA-HQ it reaches the quality of the baseline with about half the steps. The closed-form term alone, with no training, already delivers most of this improvement; the small correction network accounts for the rest.
PDF
arXiv cs.LGOct 12
Counting with Attention and LayerNorm: Norm Scaling and Representation Geometry
Ayyub Shaffy, Manoj Dhakal, Safal Shrestha, Keith W. Ross
Counting is a simple task on which transformers can nevertheless fail at long sequence lengths. We study the cost of counting in a single attention layer, up to a maximum length $L$, focusing on how softmax attention and layer normalization shape the representation from which the count is recovered. We mainly focus on regression read-out but also consider classification read-out. For regression, we show unnormalized linear attention counts exactly at parameter norms independent of $L$. For softmax attention, regression cannot count exactly with finite parameters; it recovers the count after rounding, but only when the vector parameter norms grow with $L$. We measure this cost by $B_{\min}$, the smallest bound that can be placed on every trainable vector to ensure exact counting after rounding, and derive tight rates. At fixed model dimension, $B_{\min}$ grows as $L$ without normalization, as $L^{3/2}$ under bare post-normalization, and as $L^{3/4}$ with learned post-normalization. The last rate is unexpected: post-normalization discards the magnitude that carries the count and might be expected to make counting harder, yet with a learnable gain it counts at a smaller norm than…
PDF
arXiv cs.LGOct 12
IND-Eval: Aligning Evaluation and Simulation for Industrial Time Series Foundation Models
Vebjørn Haugland, Pavel Gulin, David Foss, Peet Cremer, Erlend Aune +3
We introduce IND-Eval, a public benchmark that organizes industrial time series across domains into source-specific forecasting tasks. Relative to established benchmarks such as GIFT-Eval, it emphasizes finer sampling resolutions and a greater prevalence of multivariate forecasting. Evaluating Chronos-2, TiRex-2, and TimesFM-3, we find that TimesFM-3 achieves the lowest source-balanced aggregate nMASE and nCRPS and leads seven of nine sources under each metric; source-specific exceptions reinforce the need for domain-representative evaluation for model selection. These findings also motivate improving domain alignment during pretraining, where real industrial data are often too scarce to close domain-specific gaps directly; we therefore investigate whether a domain's statistical structure can guide simulator design. In a case study on two offshore well-monitoring regimes, we improve a general simulator's coverage using an oscillator-augmented simulation pipeline. This lowers forecasting error in the target domain but reduces performance on the subset of GIFT-Eval with natively univariate targets. A 50/50 mixture of the general and augmented simulation recipes achieves the lowest…
PDF
arXiv cs.CLOct 12
SIREN: Situation-aware Index for Response and Emergency ActioNability in Crisis Translation
Maria Carmen Staiano, Lifeng Han, Johanna Monti, Francesca Chiusaroli
Machine translation (MT) is increasingly utilized in multilingual crisis communication, yet conventional evaluation does not directly assess whether translated emergency messages preserve their actionability. We introduce SIREN (Situation-aware Index for Response and Emergency ActioNability), a human evaluation framework assessing whether translation choices compromise protective action, directive force, and urgency of the source text. We evaluate SIREN in two complementary settings. At the error level, we apply it to HOPE-annotated Italian--English translations produced by ChatGPT-4o and Google Translate: 31.63\% and 48.73\% of errors, respectively, compromise actionability, predominantly by affecting the protective action. At the message level, we evaluate English--French translations produced by TranslateGemma-4B and Google Translate, with actionability preserved in 85.34\% and 92.67\% of translations, respectively. TranslateGemma-4B failures predominantly weaken directive force, whereas Google Translate failures more often compromise protective actions and receive Major impact ratings. These findings show that translation systems can differ not only in how often actionability…
PDF
arXiv cs.LGOct 12
Learning Incompressible 3D Flows from Sparse Samples: A Set Transformer Approach to Divergence-Free Kernel Fitting
Ramzi Idoughi, Radouan Boukharfane, Peter Wonka
Recovering divergence-free velocity fields from sparse and corrupted observations requires reconciling physical consistency, expressive representations, and robustness to missing data. We introduce DFK-Former, a set-to-field transformer that reconstructs divergence-free velocity fields from sparse, noisy, and irregularly sampled 3D observations. The model is inherently invariant to the number and ordering of input samples and predicts the parameters of a divergence-free kernel representation, producing continuous, mesh-free velocity fields that satisfy incompressibility exactly by construction rather than approximately through soft constraints or projection operators. Unlike existing divergence-free kernel approaches, which estimate kernel coefficients via a separate optimization for each field, DFK-Former predicts these coefficients directly in a single forward pass. This eliminates costly iterative fitting while providing a learned prior that enables accurate reconstruction even when observations are insufficient to uniquely determine the field. To enhance representational power, we introduce adaptive and anisotropic divergence-free kernels that preserve exact incompressibility…
PDF
arXiv cs.LGOct 12
Learning Deployable Causal Action Geometry under Temporal Non-Stationarity
Changjian Liu, Tianyu Wang, Yuwei Xu, Xiaoxuan Deng, Zhilin Zhang +4
Learning a response law for continuous decisions from observational time series is central to many real-world decision systems, yet temporal non-stationarity poses a fundamental challenge: as outcomes drift over time, naively pooled models can conflate action effects with shifting baselines and even reverse action rankings. Even when the one-step response is identifiable, unrestricted cross-time generalization remains fundamentally ill-posed. We therefore seek the part of the response that remains stable for decisions even when outcome levels do not. We propose deployable causal action geometry: the action-response shape that remains after anchoring away action-independent level shifts on a selected link scale and profiling out positive amplitude variation. Building on this target, we develop a two-stage orthogonal estimator that first obtains cross-fitted pilot estimates of anchored responses and then performs honest profiled selection over link, representation, and shape classes. The resulting estimator admits oracle guarantees for the restricted target and, under approximate persistence, produces decision rules that remain near optimal in future periods. Experiments on…
PDF
arXiv cs.CLOct 12
SuPER-Mamba: Surprisal Prioritization for Extended-Context Routing in Mamba
Zhetong Zhang, Gayan K Kulatilleke
State space models provide efficient linear-complexity processing for long sequences, but their performance frequently degrades as context length grows. We propose SuPER-Mamba, a training-free framework that uses Surprisal as a model-intrinsic signal for long-range state routing in pretrained Mamba models. SuPER-Mamba computes position-wise Surprisal from next-token predictions, aggregates neighboring responses through Local Pooling, and uses the resulting scores to prioritize Global-Channel updates without query-dependent scoring or additional training. We evaluate SuPER-Mamba on three state-space models across the LongBench-E benchmark. The results show that SuPER-Mamba improves the average score from 8.06 to 15.69, corresponding to a 94.7% relative gain over the Base Models and a 13.1% improvement over the state-of-the-art prior baseline. Ablation and length-wise analyses further support the effectiveness of the proposed routing framework.
PDF
arXiv cs.LGOct 12
ACED: Reference-Anchored Aggregation of Natural-Language and Executable Evidence for Mathematical Reasoning
Yiyi Lu, Jiaxiang Geng, Bing Luo
Natural-language self-consistency and executable programs provide complementary test-time evidence for mathematical reasoning, yet either channel may support the same semantic error. Thus we propose ACED, a reference-anchored framework that treats the self-consistency answer as the default and executable outputs as supporting evidence rather than interchangeable votes. ACED converts source-specific answer counts into smoothed supports, combines them through a weighted logarithmic pool, and overrides the reference only when a calibrated relative-evidence margin is exceeded. The same rule supports both candidate selection and admission of executable-only answers. Across five math word-problem benchmarks, ACED matches or outperforms the corresponding baselines. On GSM8K, ACED-CANDIDATE recovers 89.7% of the attainable candidate-set gain with only three damaging overrides, while ACED-ALL reaches 86.9% accuracy versus 82.6% for direct Program-of-Thought aggregation. These results show that preserving evidence provenance enables more reliable integration of natural-language and executable reasoning.
PDF
arXiv cs.ROOct 12
Language2Drive: Do Vision-Language-Action Models Really Follow the Instructions in Autonomous Driving?
Zihan You, Zehua Fan, Wenqi Lyu, Aoqi Wang, Ni Wang +17
Recent Vision-Language-Action (VLA) models increasingly use natural-language instructions to condition autonomous driving behavior. Yet existing closed-loop benchmarks primarily measure route completion, safety, and rule compliance, leaving a fundamental question unresolved: does language actually determine which feasible behavior the vehicle executes? A trajectory may be safe and successful while still violating or even ignoring the passenger's instruction. To address this, we introduce \ltd, a benchmark designed to directly test this capability. Its key evaluation unit, the paired counterfactual unit (PCU), holds the initial driving scene fixed while changing only the instruction. This design enables us to distinguish isolated instruction success from counterfactual paired success across four instruction-following scopes. To test whether this distinction persists across evaluation regimes, we instantiate Language2Drive in complementary closed-loop CARLA simulation, reconstructed real-world scenes, and open-loop driving benchmarks, including our released CARLA-Language2Drive simulator with purpose-built maps. Evaluating representative driving VLAs across these settings reveals a…
PDF
arXiv cs.CVOct 12
REEL: Learning to Retrieve, Evaluate, and Evolve Visual Memory for Any Long-Horizon Multi-Shot Video Generation
Hang Xu, Guohui Zhang, Xiaoxiao Ma, Hu Yu, Jie Huang +5
Memory-based long-video generation aims to combine user control with long-range visual consistency. We organize this process into three functional components: a planner, an adapter, and a generator. Representative multi-shot systems couple memory to generator-specific interfaces or use predefined agent workflows, rather than independently training a memory policy for cross-shot objectives. We introduce REEL, a general-purpose visual-memory planner. Through a unified tool interface, REEL learns to retrieve references, create missing visual evidence, and update persistent memory. Backend-specific adapters translate its evidence plans into supported conditioning inputs, allowing the same policy to guide different black-box video generators. To train REEL, we construct two high-quality datasets, REEL-SFT-4k and REEL-RL-1k, covering diverse interaction patterns and prompt types. Training proceeds in three stages: supervised fine-tuning, single-shot Group Relative Policy Optimization (GRPO), and multi-shot GRPO. Multi-shot GRPO carries policy-generated memory across consecutive shots, so later outcomes guide earlier reference selection and memory updates. REEL-Bench tests identity…
PDF
arXiv cs.LGOct 12
AeroChem: Closed-loop Physics-Informed State Space Modeling for Long-term Chemically-Reactive Air Quality Forecasting--Extended Version
Kien Le Trung, Tung Kieu, Dinh Duc Nha Nguyen, Cuong Do, Bin Yang +1
Accurate long-term air quality forecasting is challenging due to long-range transport, meteorological variability, and nonlinear chemical reactions underlying secondary pollutant formation. Purely data-driven models often suffer from long-horizon drift and lack physical consistency, while existing physics-informed approaches commonly follow open-loop designs that fuse neural and physical components only at the output level. We propose AeroChem, a closed-loop physics-informed state space framework for chemically reactive air quality forecasting. AeroChem adopts a two-branch co-correction design: a UDE-based process branch provides a structured but imperfect physical prior, while a Mamba-based virtual measurement branch captures long-range temporal context and produces probabilistic virtual observations. Neural Kalman Fusion couples the two branches by correcting the latent physical state at each forecasting step and feeding the posterior state back into the simulator, reducing long-horizon drift. We further introduce HanoiAir, a real-world dataset integrating pollutant concentrations, meteorology, and emission inventories. Experiments on HanoiAir and a public benchmark show that…
PDF
arXiv cs.HCOct 12
Integrating Feature Understandability into Feature Selection for Human-Centred Tabular Explanations
Nicola Rossberg, Bennett Kleinberg, Barry O'Sullivan, Luca Longo, Andrea Visentin
Existing human-centred XAI research predominantly evaluates explanations after they have been generated. However, this fails to provide actionable insights into improving accessibility. This study incorporates human-based feature understandability into feature selection to improve the generation of human-centred explanations. Natural language explanations for machine learning models trained on tabular data often cite influential features in the input data to explain a given decision. As a consequence, users' ability to understand the produced explanation hinges on their understanding of the cited features. To quantify this natural-language feature understandability, Rossberg et al. proposed the Feature Understandability Scale, which assigns numerical `understandability scores' to features based on user feedback. To evaluate the degree to which these scores can improve machine learning explanation quality, this study collects understandability scores across two datasets, proposes an understandability-aware feature selection algorithm to select features that are both understandable and informative, and trains a random forest based on these feature subsets. The SHAP-based…
PDF
arXiv cs.AIOct 12
LATCH: LLM-Assisted Timing Closure Harness for Post-Route FPGA Optimisation
Shu Gu, Matthew Youngman, Yuqin Zhao, Cristian Sestito, Ali Siddique +3
Post-route FPGA timing closure remains expert-dependent and computationally expensive. We present LATCH (LLM-Assisted Timing Closure Harness), a two-layer framework that separates large language model (LLM) orchestration from deterministic FPGA implementation and evaluation. Across sixteen designs and seven LLMs, a single-iteration study compares three agent control granularities - expert-written recipes, direct EDA operations and LLM-constructed procedures - to ask how much control an agent needs per attempt. Functional-pass rates are 98.2%, 71.4% and 17.9%, respectively; yet direct operations give slightly larger 3.4% median Fmax gains when passing, versus 3.2% for recipes. This exposes a trade-off between execution reliability and timing improvement. Informed by this trade-off, a multi-iteration study fixes the action tier at expert recipes to ask how repeated attempts are best organised, comparing a fitted deterministic heuristic with sequential LLM reasoning, branching exploration and knowledge base-guided exploration within 12 checkpoints per run. Branching raises mean maximum-frequency improvement from 10.5% (sequential) to 16.0%, and the knowledge base to 20.3%, improving…
PDF
arXiv cs.CVOct 12
Adaptive Interaction Network for Human Motion Prediction During Human-Robot Collaboration
Mengyuan Liu, Yangting Lin, Qiongjie Cui
Human motion prediction during human-robot collaboration is critical for achieving safe and efficient interactions in shared environments. Unlike previous studies that have primarily focused on humans and objects, we focus on the robot-aware human motion prediction task, which explicitly models the influence of robots on human motion. This task presents new challenges, such as capturing human-robot heterogeneity and modeling complex spatial interactions. To address these issues, we develop an adaptive interaction network (AINet) model that consists of two branches: a primary branch that predicts future human motion and an auxiliary branch that estimates robot trajectories. The two branches are jointly optimized and coupled via a Local-Global Spatial Interaction (LGSI) Module, which effectively captures fine-grained and global contextual dependencies between human and robot motion sequences. Then, we introduce an Adaptive Weighted Aggregation (AWA) Module to dynamically fuse motion features using context-dependent weights, thereby increasing adaptability across diverse scenarios. Furthermore, we adopt a coarse-to-fine prediction strategy, in which a coarse pseudo-trajectory is…
PDF
arXiv cs.CVOct 12
Answer It or Not? Towards Prompt-Adapted Adversarial Images on Vision Language Models
Shunyuan Bai, Yuchen Ren, Le Yang, Chenhao Lin, Chao Shen +1
With the advancement in language modeling, research on adversarial images has recently shifted from image classifiers to vision-language models (VLMs). Despite the new, text-prompt-driven nature of VLMs, we find that existing VLM adversaries have largely overlooked the dynamics of text prompts. In a typical use case, adversarial images can protect visual privacy by rejecting VLMs from answering questions about the image. However, existing protections are prompt-agnostic, i.e., indiscriminately rejecting any question, including those for potential legitimate use of the image. To address this limitation, we propose Prompt-Adapted (ProAda) adversarial images, which are optimized to balance the rejection of harmful prompts and the correct response of legitimate prompts. In particular, to achieve a more accurate adversarial direction, the text prompt is also iteratively updated with a simple classifier judging whether the harmfulness of the prompt remains. Extensive experiments on visual-privacy-related datasets validate that ProAda can reject over 90% of harmful prompts while allowing over 90% of legitimate ones, demonstrating superior overall performance compared to existing…
PDF
arXiv cs.AIOct 12
Weak Segmentation-Guided GAN for~Realistic Color Edition
Vincent Auriau, Emmanuel Malherbe, Matthieu Perrot
Editing the color of images in a realistic way finds many applications such as changing the perception of an image, data augmentation or film post processing. The design of an automatic tool is a complex and long addressed challenge. In particular, two properties are difficult to meet altogether: generating realistic results without artifacts and the possibility to precisely choose the future color. Conventional methods using segmentation and histogram matching maximize the controllability but also introduce a lack of realism or are complex to automate. On the contrary, GANs that specialize in realism are difficult to control. To overcome these challenges, we propose a novel GAN architecture leveraging any differentiable segmentation model. We demonstrate the genericness of our framework that presents state of the art results on different use cases. It generates images that look realistic while offering a precise color control.
PDF