Research

• Reliable request execution in streaming video generation1 paper raises it · 0 address it

  Models often fail to follow incremental user requests while maintaining state consistency in real-time video generation.

  • StreamEval: Evaluating Interactive Streaming Video Generation Modelsraises
• Brain-body mismatch in recursive self-improving agents1 paper raises it · 1 addresses it

  Evolving execution scaffolds (harnesses) can outpace or restrict the capabilities of the underlying model, leading to misalignment.

  • CoEvo-RSI: When Harnesses Evolve, Which Models Should Follow?raises · addresses
• End-to-end deep search in real-world web environments1 paper raises it · 1 addresses it

  Agents struggle to autonomously explore, integrate, and verify evidence from diverse, interactive, and heterogeneous web sources.

  • Deep Search in Real-World Web Environmentsraises · addresses
• Length generalization in state tracking1 paper raises it · 1 addresses it

  Models trained on short sequences often fail to generalize to much longer sequences without explicit progress alignment.

  • PAR: Progress-Aligned Recurrence for Length Generalization in State Trackingraises · addresses
• Evidence-grounded evaluation for audio-visual reasoning1 paper raises it · 1 addresses it

  Existing benchmarks often allow models to exploit textual or unimodal shortcuts, failing to test true multi-modal reasoning.

  • EvaOmni: An Evidence-Grounded Benchmark for Audio-Visual Reasoningraises · addresses

Named by an AI from these papers' abstracts.

• arXiv cs.CVOct 13

  Resource-Efficient 3D Shape and Orientation Estimation of Road Users using Roadside RGB Camera and 3D Radar

  Shiva Agrawal, Savankumar Bhanderi, Gordon Elger

  End-to-end deep learning pipelines for camera-radar 3D object detection are well established in driver assistance systems and autonomous vehicles; however, adapting them to roadside-mounted infrastructure presents significant challenges. On vehicles, sensor heights, pitch angles, and relative geometries remain largely uniform, allowing end-to-end models to generalize effectively. On the contrary, roadside sensor installations vary drastically in height, tilt, and field of view across locations, rendering end-to-end models prone to failure and difficult to adapt without massive location-specific datasets. Hence, instead of designing a complex end-to-end pipeline for direct 3D bounding box estimation, a low-cost, resource-efficient two-stage approach is proposed for real-time 3D shape and orientation estimation. The first stage utilizes any off-the-shelf, state-of-the-art method to extract 2D camera bounding boxes and associated 3D radar points for each road user. The proposed second stage then processes these inputs to construct 3D oriented bounding boxes where radar data determines 3D position, predefined templates define size for each road user, and a tiny neural network…

  PDF

  Summarize this
• arXiv cs.CLOct 13

  Do Factuality Methods Make LLMs More Factual? Reproducibility and Fair Comparison

  Pratuat Amatya, Vinay Setty, V Venktesh, Avishek Anand

  Large Language Models (LLMs) are aligned to human preferences, after pre-training and supervised fine-tuning steps. However, standard RL alignment steps such as RLHF do not focus on factuality of LLMs, hence they may generate non-factual information, which could result in unintended consequences. In response, a number of factuality alignment approaches have been proposed in the literature which claim to improve factuality of LLMs on their own benchmarks. However, these methods have not been reproduced independently and are also not comparable since each uses a different base model, training data, evaluation set, judge, and metric. In this paper, we present the first independent reproduction of five factuality alignment methods, which span on-policy RL (PPO, GRPO, and Dr.~GRPO) and offline preference optimization (DPO and KTO), and compare them on a common benchmark with common evaluation metrics. We found that none of these methods reproduces in full, and on the common benchmark none of the methods significantly outperforms the base model. On closer inspection, the rewards optimize for format, length, or brevity rather than factuality and relevance, whereas the choice between…

  PDF

  Summarize this
• arXiv cs.CLOct 13

  Revisiting the Estimation of Unigram Surprisal in Computational Psycholinguistics

  Zachary Hopton, Francesco Ignazio Re, Samuel Kiegeland, Andreas Opedal, Eleanor Chodroff +1

  Contextual and unigram surprisal are standard predictors of reading time in computational psycholinguistics. While contextual surprisal is typically derived from neural language models, unigram surprisal is usually obtained from independent corpus counts. Although both quantities are deterministic functionals of a single underlying distribution---capturing conditional and marginal structure respectively---this practice breaks their probabilistic link and may introduce estimation error from the mismatch. We propose three principles for estimating unigram surprisal in psycholinguistic research, including the requirement that both quantities be derived from the same language model. We operationalize this principle by introducing a Monte Carlo estimator of unigram surprisal from a language model, along with a marginalized variant that has lower variance empirically. When unigram surprisal is re-estimated under this unified framework, we find evidence that predictors change in their predictive contribution to reading time. We also confirm prior findings that frequency can be a stronger predictor of processing effort than contextual surprisal under this unified framework.

  PDF

  Summarize this
• arXiv cs.LGOct 13

  Not All Drift Is a Mechanism: Tracing Prompt Adaptation in LLMs

  Mikhail Aleksandrov, Nail Bashirov, Maksim Ivanov, Andrew Tsukanov, Timofey Karyagin +4

  Prompt-based adaptation offers several ways to specialize a frozen language model, ranging from natural-language prompt optimization to learned continuous prompts. These methods are usually compared through downstream performance, although similar outputs need not arise from similar internal computations. We study how discrete prompt optimization, prompt tuning, and prefix tuning alter the processing of dense and mixture-of-experts language models. Our analysis shows that the location of the adaptation predicts how task information is carried to the output: optimized text primarily changes response construction, input-level prompts write their influence into content representations, and layer-wise prefixes maintain direct control through attention. In MoE models, these differences further induce distinct expert-routing patterns. At the same time, common representation-level measurements respond strongly to generic context changes and do not reliably distinguish useful adaptations from matched placebos. We argue that understanding prompt adaptation requires separating representation drift from the part of that drift that is aligned with, and causally used by, the model's task…

  PDF

  Summarize this
• arXiv cs.IROct 13

  Graph-free Retrieval with Graph-Modified Embeddings

  Federica Santi, Vasilije Marković, Daniel Scott, Lazar Obradović

  Dense vector retrieval can miss evidence connected through intermediate entities, while direct graph retrieval requires access to the graph at query time. We compare five offline graph-based embedding transformations and strategies for using the resulting graph-modified embeddings alongside the originals, without query-time graph access. On a synthetic professional-network benchmark with complete supporting-evidence sets, direct replacement of the original embeddings reduces evidence recovery. Multi-stage strategies improve recovery by using graph-modified embeddings to guide the search while retaining the originals for semantic relevance. On questions requiring linked facts or comparisons among candidates, the strongest configuration improves recovery by up to 25.9% relative to plain vector retrieval. It also matches baseline recovery with 40% fewer returned nodes. Controls confirm that graph information contributes beyond multi-stage retrieval alone. Across the tested methods, retrieval performance depends more on how graph-modified embeddings are used than on how they are produced.

  PDF

  Summarize this
• arXiv cs.CLOct 13

  Prompt-Injection Probes Learn the Conversation, Not Just the Injection

  Kaan Kale, Sriram Vishwanath

  Linear probes on a model's hidden states are used as cheap monitors for indirect prompt injection: they screen the tool outputs an agent reads and send suspicious ones to a slower second check, so every false alarm has a cost. But a probe learns whatever separates its training examples. The standard evaluation of injection probes can be passed without the model: conversation position and text lengths alone reach 0.91-0.98 AUROC. When each attack is compared with the same conversation without the injection, or with harmless text formatted like an injection, standard probes flag most of these harmless cases. We add such cases to the training data as matched negatives. Across six open models, in applications seen during training and at the default threshold, changing only the training data cuts false alarms on injection-free conversations from 41-80% to 4-27%, and on harmless look-alikes from 92-98% to 3-16%. With a threshold set on normal traffic, our probe still catches a median 95% of the attacks that fooled the agent (91% without our data). In new applications, false alarms stay low, but detection depends on the model and on how the threshold is set. The same data also helps a…

  PDF

  Summarize this
• arXiv cs.LGOct 13

  Multi-Stream Residual Computation in Diffusion Language Models

  Ekaterina Alimaskina, Suren Kazarian, Gleb Molodtsov, Aleksandr Beznosikov

  Diffusion language models reconstruct masked tokens in parallel, offering an alternative to autoregressive generation. Yet their Transformer backbones typically carry visible evidence and evolving masked predictions through a single residual stream. We equip masked diffusion models with multiple residual streams that persist through depth and adaptive routing between them, then investigate how they support these complementary roles. On the pretraining task, two streams reduce reconstruction perplexity by 5.71% on validation data and 5.13% on average across external corpora compared with standard residual connections. We observe that, without predefined roles, visible and masked positions learn distinct routing patterns. Causal interventions show that this distinction organizes read and write routing, while token-specific write strength remains important within each role. Guided by these findings, a model trained with role-conditioned routing recovers half the validation gain from adding a second stream. State interventions explain the benefit of the additional stream: it preserves early token representations for later reuse while evidence accumulates at masked positions. This…

  PDF

  Summarize this
• arXiv eess.SPOct 13

  Overcoming Catastrophic Forgetting: Continual Learning for Radar Waveform Classification

  Mohamed Rabie, Chinthana J. Panagamuwa, Konstantinos G. Kyriakopoulos

  Automated radar waveform recognition classifies the waveform and modulation type of a received signal. As new waveform variants appear over time, a deployed classifier must learn them without retraining from scratch. Catastrophic Forgetting occurs when learning new waveforms overwrites prior knowledge. Continual Learning (CL) methods tackle this challenge, but prior radar studies only evaluate a few methods on narrow benchmarks. Practitioners lack evidence on which method to deploy or which mechanisms are effective. This work presents the first large-scale benchmark of continual learning for radar waveform recognition. Eighteen CL methods are evaluated on a sequential ten-task problem, drawn from four public datasets spanning 54 waveforms, under task- and class-incremental (TIL, CIL) settings and single- and multi-epoch regimes. Methods that retain data from old tasks lead both TIL and CIL settings. Plain replay alone closes 77-88% of the gap between the lower and upper practical limits under TIL, but only 46-55% under CIL. The internal mechanisms of the leading methods are ablated and statistically tested to identify effective mechanisms. Each ablation is paired against its full…

  PDF

  Summarize this
• arXiv cs.CVOct 13

  Bifocal: Training-Free Mixed Granularity Visual Token Pruning for Multimodal LLMs

  Peiran Yin, Hao Wu, Zihao Yang, Fengyu Zhou, Yijuan Liang +4

  Visual token pruning for multimodal large language models (MLLMs) appears highly effective, with existing methods retaining over 95% of unpruned performance on common VQA benchmarks using a quarter of the visual tokens or fewer. However, our extensive evaluation of ten methods across three MLLM families and five ability groups reveals a critical gap: strong general performance often comes at the cost of severe degradation on fine-grained tasks such as OCR and visual grounding. We trace these failures to two limitations of the prevailing paradigm of retaining the highest-ranked native patches. A single importance ranking overlooks the complementary evidence required by different tasks, while sparse patch selection disrupts both image content and spatial integrity. To address these limitations, we propose Bifocal, a training-free, two-stage pruning method built on a mixed-granularity framework. It allocates separate budgets to query-focused and image-intrinsic evidence, complemented by a pooled coarse representation of the entire image. Before the LLM, Bifocal matches question words to visual regions through a soft conjunction balanced against norm-debiased image saliency, while…

  PDF

  Summarize this
• arXiv cs.DCOct 13

  LunaTP: Enabling Efficient and Scalable Tensor Product for Equivariant MLIPs

  Yuanchang Zhou, Mingzhen Li, Chen Wang, Xiangyu Zhang, Guangming Tan +1

  Equivariant machine learning interatomic potentials (MLIPs) promise atomistic simulations with accuracy approaching that of quantum-mechanical calculations. However, the high computational cost of their core Clebsch--Gordan tensor product (CGTP) convolutions severely limits model scalability and efficiency. In this paper, we rethink the parallel execution of CGTP convolutions and introduce LunaTP. Built on node-centric execution, LunaTP exploits path-group parallelism and multi-level reuse to accelerate CGTP convolutions and higher-order derivative computation while preserving the underlying mathematical formulation. On an NVIDIA H100 GPU, LunaTP achieves kernel speedups of up to 250.0$\times$ over e3nn and 17.1$\times$ over OpenEquivariance. It also delivers end-to-end training throughput gains of up to 28.7$\times$ over e3nn and 3.11$\times$ over OpenEquivariance. Finally, LunaTP demonstrates scalability and robust performance across models, workload scales, and GPUs, delivering substantial acceleration for training and atomistic simulation with high-accuracy equivariant MLIPs.

  PDF

  Summarize this
• arXiv nlin.CDOct 13

  Beyond RMSE and Granger Gain: Multi-Horizon Forecast-Error Entropy for Nonlinear Predictive Coupling

  Andrei Velichko

  We investigate whether the past of an auxiliary time series provides predictive information about a target beyond that contained in the target's own history. We compare matched out-of-sample target-only and target-plus-source forecasts and introduce the forecast-error distribution entropy (FEDE) predictive-causality framework, where predictive causality is understood in the Granger sense: auxiliary history is informative when it improves prediction beyond the target's own past. FEDE quantifies how the full signed forecast-error distribution changes across prediction horizons. Controlled nonlinear benchmarks hide source-target dependence behind nonlinear transformations not supplied to the predictors. LightGBM recovers these hidden channels, whereas Ridge does not. Across four equal-power nonlinearities and four noise levels, the mean response-sensitivity statistic for FEDE remains 29.00, 27.47, 23.22, and 28.67, compared with 14.09, 10.68, 12.67, and 12.71 for mean log-RMSE gain. Directional and source controls separate the true source-to-target channel from the reverse direction and from independent periodic, quasiperiodic, chaotic, and autoregressive auxiliaries. Chronological…

  PDF

  Summarize this
• arXiv cs.LGOct 13

  PRISM: Calibrating Black-Box Judges with Counterfactual Probes

  Kakei Yamamoto, So Kuroki

  Large language models are increasingly used as judges to reduce reliance on costly human evaluation, yet their scores can systematically disagree with human judgments. We ask whether responses to an explicitly imposed evaluative bias can help correct a judge's implicit scoring biases. We introduce PRISM (Probe-based Residual Inference of Scoring Misalignment), which holds the evaluated content fixed and measures score changes when attributes are emphasized or de-emphasized. A local sensitivity model motivates representing these responses as a surrogate Jacobian. Ridge regression on human labels learns a correction to the baseline score. The resulting scoring protocol is rubric-free: it uses overall scores without requesting criterion-level ratings. In the main Jev and Sol comparisons on SummEval summarization and HANNA story evaluation, PRISM and its learned-baseline variant significantly improve agreement with human rankings over uncalibrated scores while remaining competitive with rubric-based methods. A controlled SummEval comparison yields similar agreement for rubric-derived quality probes and style probes, supporting calibration without reproducing rubric criteria. The…

  PDF

  Summarize this
• arXiv cs.CVOct 13

  ReDiS: Reasoning-Diagnosis Self-Evolution for Multimodal Reasoning in Remote Sensing

  Yi Liu, Wentao Jiang, Shuo Ni, Zhiming Luo, Di Wang +3

  Multimodal large language models (MLLMs) have shown strong potential for remote sensing understanding, yet reliable reasoning remains challenging when tasks require fine-grained visual grounding and multi-step inference. Existing approaches typically rely on either costly pre-constructed reasoning trajectories or self-generated signals such as response consistency, which can reinforce shared errors and provide unreliable supervision. We introduce \textbf{Reasoning--Diagnosis Self-Evolution (ReDiS)}, a framework that separates reasoning exploration from candidate evaluation while allowing the two processes to evolve jointly. ReDiS instantiates two role-specific experts from a shared multimodal backbone: a \textbf{Reasoner} that explores diverse visual evidence--answer candidates and a \textbf{Diagnoser} that jointly evaluates the complete candidate set and provides credibility-aware feedback. As the Reasoner evolves, it exposes new candidate distributions and failure modes; the Diagnoser adapts to these changes and, in turn, reshapes the learning signal for subsequent exploration. To handle groups in which all sampled answers are incorrect and group-relative advantages vanish, we…

  PDF

  Summarize this
• arXiv cs.CVOct 13

  Noise2Match: Self-Supervised Low-Dose CT Denoising via Adaptive Inter-Slice Matching

  Langrui Zhou, Guang Li, Xinyu Huang, Ziteng Zhou, Zuyang Huang +3

  With the rapid development of deep learning, supervised convolutional neural network methods have greatly improved the performance of low-dose computed tomography (CT) denoising. However, they require paired noisy-clean training data, which is difficult to obtain in practice. Some classic self-supervised denoising methods rely on the assumption of pixel-wise independent noise, making them ineffective for correlated noise in low-dose CT (LDCT) images. Considering the high similarity and weaker noise correlation between adjacent CT slices, several recently proposed self-supervised methods use adjacent LDCT slices for training. Nevertheless, these approaches fail to effectively account for the non-rigid misalignment between slices caused by anatomical variation, hindering them from satisfying the equal-mean condition required by the classic Noise2Noise framework. In this paper, we propose Noise2Match, a self-supervised LDCT denoising method based on adaptive inter-slice matching. Noise2Match introduces an inter-slice matching network to model the label transition process between adjacent slices, and then applies correction to the denoiser's outputs to better satisfy the equal-mean…

  PDF

  Summarize this
• arXiv cs.AIOct 13

  Delegating Earth science model calibration to knowledge-guided LLM agents

  Zhanliang Zhu, Ziwei Li, Liujun Zhu, Yuchen Liu, Junliang Jin +1

  Applying process-based Earth science models to new sites and questions often requires expert calibration decisions. Reliable delegation to language-model agents must preserve scientific competence and reproducibility. Here we develop a general calibration harness (GCH) for end-to-end delegation from a calibration request to assessed results. Constrained by a knowledge infrastructure (KI) and a validation convention, agents define parameter domains, observation mappings and objectives, and generate model-specific code. GCH checks the formulations against the same declarations and freezes them before numerical search and assessment, which require no further agent judgement. Agent-authored workflows executed across six model families, with assessment identifying unmet criteria. In snow-model tests, five of five knowledge-guided specifications executed on the first attempt, compared with none of five given only the model name, achieving validation Nash-Sutcliffe efficiency (NSE) of 0.81-0.94 against 0.57 for defaults. Under a common objective, independent GR4J formulations yielded scores within 0.001 NSE; re-evaluating eleven saved parameter vectors reproduced their metrics. In ten…

  PDF

  Summarize this
• arXiv cs.LGOct 13

  Beyond Task Success: A Theory of Representation Reuse

  Zibo Meng, Andrew C. M. Austin, Alin Achim

  A learned representation is useful beyond its source task only if later tasks can make use of what the encoder has already learned. Source-task performance, however, gives no guarantee that the representation itself will remain useful once the original head is removed. We study representation reuse with respect to a specified family of future tasks. For such a family, we define the task-relevant state as the coarsest deterministic state sufficient for all of its tasks. A larger task family can require a finer state, and losing a required distinction makes at least one future task unrecoverable on a target support containing that conflict. Exact reuse also depends on how the retained information is presented to the downstream rule. We separate this into structural accessibility, which concerns whether the required distinctions remain recoverable, and coordinate consistency, which concerns whether those distinctions can be interpreted by the same downstream rule across samples. Both failure modes appear separately in the experiments. Reuse improves as task-relevant distinctions become more accessible. Reversible sample-dependent coordinate changes can sharply reduce reuse even when…

  PDF

  Summarize this
• arXiv cs.CVOct 13

  SchemaPose: RGB-Based Category-Level Pose Estimation with Parametric Category Schema

  Shuang Wu, Jiude Wei, Cewu Lu, Jianhua Sun

  RGB-based category-level 9D pose estimation remains highly challenging because a monocular system must generalize across unseen object instances while jointly inferring 3D translation, 3D rotation, and 3D size. Unlike instance-level pose estimation, the category-level setting requires the network to learn both what is shared across objects within a category and how individual instances vary in structure. This challenge is amplified in the RGB-only setting, where pose cues, category-level commonality, and instance-specific variation are entangled in appearance without direct geometric constraints, making it difficult for existing frameworks to learn a representation that is truly aligned with the category-level estimation objective. To address this problem, we propose SchemaPose, a schema-guided framework for RGB-based category-level pose estimation. SchemaPose equips the estimation pipeline with an explicit parametric schema for modeling category-level regularities together with structured instance variation, and uses the inferred schema variables to guide pose-related prediction in an end-to-end query-based framework. The same formulation also supports template instantiation,…

  PDF

  Summarize this
• arXiv cs.CVOct 13

  Hallucination-aware Faithful Reasoning in Remote Sensing

  Yi Liu, Jing Zhang, Xiang Feng, Xiaoyu Tian, Haonan Guo +3

  Multimodal large language models (MLLMs) have demonstrated promising capabilities for remote sensing reasoning, yet they frequently generate visually unsupported reasoning that contradicts the visual evidence. Existing post-training methods optimize primarily for final-answer correctness, providing limited supervision for identifying and correcting hallucinations that arise during the reasoning process. To address this limitation, we propose \textbf{FaithRS}, a hallucination-aware self-reflection framework for faithful reasoning in remote sensing. We first construct \textbf{SFHD-43K}, a dataset of 43K structured, fine-grained hallucination annotations, and train a detector to identify hallucination types, underlying causes, and supporting visual evidence. FaithRS then incorporates this diagnostic feedback into a Safe Detector-Guided Corrective Rollout framework, where a safety-aware gate selectively determines whether and how to revise the response. Training is driven by a composite reward that jointly optimizes answer accuracy, reasoning faithfulness, hallucination reduction, format compliance, and revision safety. Experiments with Qwen3.5 backbones (0.8B, 4B, and 9B) show…

  PDF

  Summarize this
• arXiv cs.ROOct 13

  Visual Sevoing from Lines

  Nicolas Andreff, Bernard Espiau, Radu Horaud

  In this work, we present a fundamentally new approach to visual servoing using lines. It is based on a theoretical and geometrical study of the main line representations which allowed us to define a new representation, the so-called binormalized Plucker coordinates. They are particularly well suited to visual servoing. Indeed, they allow the definition of a proper image line alignment concept. The control law which realizes such an alignment has moreover several properties: partial decoupling between rotation and translation, analytical inversion of the motion equations and global asymptotic stability conditions. This control law was validated both in simulation and experimentally in the specific case of an orthogonal trihedron.

  PDF

  Summarize this
• arXiv cs.CROct 13

  Pin It on Anyone: Certified Targeted Displacement of Multi-Bit LLM Watermarks Without the Key

  Paweł Batorski, Przemysław Spurek, Paul Swoboda

  Multi-bit watermarking embeds a message, typically an account identifier, into LLM output so that harmful text can be traced to its origin. We show an attack technique that allows to alter the watermarking message. This allows to, for example, exchange the embedded account ID to an arbitrary different one. The attacker mainly needs access to a few accounts for generating LLM output and model logits, but crucially not the secret key used to watermark. The attacker then rewrites the text, keeping its meaning, so that the watermarking message decoder recovers the watermarking message embedded by the attacker. We are, to our knowledge, the first to propose such an attack, which we call a targeted displacement. Theoretically, we present upper and lower bounds on the probability of our attack succeeding. This bound depends on the number of accounts the attacker has access to, the length of the message and some characteristics of the given text. Our attack can succeed whenever we can bound the ambiguity of the generated text well enough. Empirically, we test our attack technique against five watermarking methods and four LLMs. Attack success tracks our predicted bounds, allowing us to…

  PDF

  Summarize this

• Anomaly detectors30−14.3%
• Adversarial training42−16.0%
• Forecasting time63−18.2%
• Federated learning37−19.6%
• CAD models12−25.0%
• Frontier LLMs380−25.5%
• Inference & serving215−25.6%
• 3D scene127−28.7%