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.CVOct 18
MotionShift: Environment-Compatible Motion Transfer via Planner-Evaluator Synergistic Adaptation
Yanchen Liu, Junyao Gao, Yanan Sun, Wensheng Chen, Guangming Lu +1
Existing motion transfer methods excel at exact, rigid motion replication from reference videos to target scenes, whereas they often fail to account for the compatibility between the transferred motion and the target scene environment in accordance with physical laws. In this work, we propose MotionShift, a novel motion transfer framework that achieves high-fidelity motion transfer while ensuring physical compatibility with the target scene. In particular, we design a planner--evaluator iterative motion adaptation mechanism, in which a Large Language Model (LLM) acts as the planner to generate motion trajectories by leveraging its strong semantic reasoning capabilities, while a Vision-Language Model (VLM) serves as the evaluator to rectify the motion based on its superior visual perception and scene understanding. Through this planner--evaluator synergistic reasoning process, the motion is adapted to the target scene in a training-free manner. The adapted motion is then used as a generative condition for an image-to-video (I2V) model to render videos in the target scene. Extensive experiments demonstrate that MotionShift achieves high-fidelity and physically compatible motion…
PDF
arXiv cs.CVOct 18
The Explainability Illusion: Must ViTs Exhibit Patch-Decoding Interpretability?
Ronen Schaffer, Hila Manor, Tomer Michaeli
Transformers are widely assumed to exhibit token-decoding explainability. In particular, in vision transformer (ViT) classifiers, decoding individual patch tokens has become a common diagnostic tool due to its tendency to yield human-interpretable outputs. In light of the increasing popularity of this approach, an important question is whether token-decoding explainability is an inherent property of transformers that should be expected to hold across architectures, scales, and training objectives, or merely an artifact of some implicit bias. In this paper we systematically study token-decoding explainability across diverse ViT settings, spanning architectures, scales, and training objectives, using both controlled experiments and real-world models. We find that while some models indeed exhibit aligned and interpretable token decodings, others exhibit either inverted explainability maps or a complete lack of correlation with the image semantics. As we show, these tendencies toward different explainability behaviors are not intrinsic to the architecture and can vary arbitrarily with changes in the optimization landscape. We provide theoretical support for these observations by…
PDF
arXiv cs.ROOct 18▲ 2
Vision as Proprioception: Estimating Humanoid Robot Pose from Video
Jiaxi Jiang, Matthias Heyrman, René Zurbrügg, Marco Hutter, Christian Holz
Estimating a humanoid robot's internal state from video has a wide range of real-world applications but remains unexplored. During interactions with a robot, its onboard state information may be unavailable due to privacy, ownership, or communication constraints. Meanwhile, online and AI-generated robot videos provide rich sources of data but typically lack corresponding joint configurations, limiting their direct use in robot learning. To address these issues, we present HumanoidPose, a new framework that treats vision as proprioception to recover full-body joint configurations in world space from video alone. Specifically, we combine pretrained human-pose features with robot kinematics in a unified model that predicts each embodiment's joint configurations. We retarget human motions to sixteen different humanoid embodiments, enabling scalable learning entirely from synthetic data. To improve real-world generalization, we further leverage unlabeled online videos through self-training to develop a 2D robot-pose detector. In our evaluation, HumanoidPose improves joint-angle and joint-position accuracy over the evaluated baselines and reduces joint-angle error by 18-32% relative to…
Code
arXiv cs.LGOct 18
A discrete-continuous-time stochastic framework for attention-deficit/hyperactivity disorder-related symptom modeling and pharmacological intervention via methylphenidate
Oana-Maria-Catalina Crisan
This paper presents an original mathematical and computational framework for modeling the efficacy of methylphenidate as an optimal control policy acting on the nonlinear dynamics of attention deficit hyperactivity disorder. Neural processes in ADHD are conceptualized as stochastic processes with trajectories that inherently converge towards stable, yet dysfunctional patterns associated with clinical symptoms. The pharmacological intervention is mathematically formalized as an external control signal that reassesses the system's drift and redirects these trajectories towards neurotypical regimes. To bridge these theoretical stochastic models with empirical clinical data, latent representations are inferred using a novel deterministic hybrid deep learning architecture, combining a one-dimensional convolutional neural network and a Vision Transformer, trained on preprocessed functional magnetic resonance imaging data.
PDF
arXiv cs.CVOct 18
Learning Lane-Structured Conditioning Fields for Online HD Mapping
Andrea Bertogalli, Anthony Dell'Eva, Marcello Ceresini, Federico Pirazzoli, Lorenzo Cipelli +3
High-definition maps provide critical structural information for downstream autonomous driving tasks. Recent methods increasingly rely on external priors to improve prediction accuracy and robustness. Yet, existing prior representations expose a trade-off: dense rasters are easy to integrate but ignore certain map geometric properties, while sparse vectors preserve geometric structure but require dedicated encoders and are difficult to plug into existing architectures. Moreover, external priors can be inaccurate, costly to acquire, or difficult to maintain, motivating a structural representation that can provide geometric guidance while remaining learnable and broadly applicable. We address this limitation with the Lane Field, a dense BEV-aligned geometric representation that encodes local lane structure at each spatial location and can be either predicted from onboard observations or constructed from external map priors. Building on this representation, we introduce a plug-and-play framework that enhances online HD mapping through two complementary mechanisms: BEV feature modulation, which injects lane-structured cues into latent BEV features, and deformable attention guidance,…
PDF
arXiv cs.LGOct 18
Data-driven forecasting of tropical cloud forest phenology: A dynamical systems and machine learning hybrid approach
Pedro Garcia, Saul Flores
Forecasting how species and ecosystems respond to climate change is a critical challenge in ecology, particularly in hyper-diverse tropical biomes. While traditional phenological models often rely on preconceived functional forms, this study introduces a data-driven hybrid approach that integrates dynamical systems theory with machine learning to forecast flowering and fruiting cycles. Using a robust 35-year dataset from a Venezuelan tropical cloud forest, we reconstruct the system's state-space using delay vectors inspired by Takens' theorem, incorporating climate forcing variables such as temperature and precipitation. The model was trained using Gaussian Process Regression, providing both point predictors and explicit uncertainty estimates. Our results clearly suggest that the synergy between dynamical systems and machine learning effectively captures the non-linear complexities of ecological time series. Specifically, the model achieved higher predictive accuracy for flowering and fruiting. This hybrid framework offers a scalable tool for anticipating phenological mismatches and informing conservation strategies in the face of global environmental change.
PDF
arXiv cs.AIOct 18
Bridging Concepts: Multi-Agent Reasoning over Scientific Concept Graphs for High-Impact Research Prediction
Donggyu Yoon, Minsung Hwang, Juneha Baek, Donghyuk Shin, Joyce Jiyoung Whang
Within a research community, new topics often emerge when previously unconnected concepts are first studied together. We construct scientific concept graphs (SCGs)--domain knowledge graphs whose nodes are fine-grained research concepts extracted from paper text by LLMs and whose edges capture their co-occurrence in papers--and study the task of forecasting high-impact concept pairs, i.e., discovering concept pairs that are currently unconnected but will have high impact when connected. To this end, we introduce new benchmark datasets constructed from CIKM, KDD, and SIGIR conference papers, with varied prediction settings, including impact forecasting for emerging concepts unseen during training. We propose MiroGraph, a Multi-agent reasoning framework with scientific concept Graphs, in which a feature designer agent designs predictive features for a given concept pair from structural, semantic, and trend perspectives, and then three LLM agents compute the actual feature values from the enclosing subgraph of the concept pair. Using these feature values, a classifier designer agent constructs a classifier that predicts the final impact labels. MiroGraph outperforms various impact…
PDF
arXiv cs.CVOct 18
Holo4D: Holistic 4D Reconstruction as Geometric Control for Video Diffusion
Yushi Lan, Zeren Jiang, Koichi Namekata, Xingang Pan, Chuanxia Zheng +1
Synthesizing a monocular video from a new camera trajectory requires preserving the observed scene geometry and motion while completing regions that become newly visible. Feed-forward 4D reconstructors recover the structure of the observed scene, whereas video diffusion models provide a generative prior for completing unseen content. We introduce Holo4D, a video reshooting framework that uses reconstructed 3D trajectories as a holistic source-view 4D scaffold. We project these trajectories into the requested views and encode their geometry and source appearance to guide a pretrained video diffusion model. Together with the source video and target cameras, the scaffold grounds generation in reconstructed observations while leaving unsupported regions to the generative prior. Experiments demonstrate the value of trajectory-based conditioning for camera control and novel-view synthesis. The framework accommodates different 4D reconstructors without retraining the video generator, allowing it to benefit from future advances in source reconstruction. More details can be found in our project page.
PDF
arXiv cs.CVOct 18
GeoART: Geometry-Aware Refinement via Test-Time Scaling for Camera-Conditioned Video Diffusion
Liudi Yang, Ziyuan Liu
Camera-conditioned video diffusion models often suffer from inaccurate camera control and geometric inconsisten- cies because camera constraints and estimated geometry are only weakly enforced during denoising. Existing reme- dies often require costly geometry-aware fine-tuning or ad- ditional 3D supervision. We introduce GeoART, a training- free self-refinement framework that improves camera con- trollability through geometry-aware test-time scaling. At selected denoising steps, GeoART generates multiple can- didates within the Predict-and-Perturb cycle and eval- uates them using a geometry prior, without directly modify- ing the denoising trajectory. A confidence gate suppresses unreliable geometric evidence, while rank-calibrated prob- abilistic selection combines score magnitude and relative rank to choose the next refinement state. Experiments demonstrate consistent improvements in camera controlla- bility, multi-view consistency, and visual quality over exist- ing sampling and self-refinement methods, without training or modifying the pretrained video diffusion model
PDF
arXiv cs.LGOct 18
EG-GRPO: Evidence-Guided Step-level Credit Assignment for Deep Search Agents
Sijia Luo, Mengjie Gao, Yuxiao He, Mengshu Sun, Cuiping Li +2
LLM-based search agents demonstrate strong capabilities in long-horizon information seeking and reasoning, typically trained via reinforcement learning. However, existing approaches predominantly rely on trajectory-level outcome rewards, providing limited supervision for complex search and reasoning processes. Although step-level credit assignment offers a promising solution, obtaining reliable and task-grounded supervision for open-ended search remains challenging. In this paper, we propose Evidence-Guided Group Relative Policy Optimization (EG-GRPO), a framework that derives step-level supervision from the evidence annotations available in synthetic deep search data. EG-GRPO identifies the first supporting citation for each required evidence claim and uses the newly acquired evidence to construct step-level process rewards. By representing the accumulated evidence as an evolving knowledge state, EG-GRPO further performs state-conditioned relative advantage estimation and combines the resulting step-level signal with the standard trajectory-level outcome advantage. Experiments on five challenging deep search benchmarks show that EG-GRPO generally outperforms standard GRPO and…
PDF
arXiv cs.CLOct 18▲ 4
SPARC: Spoken Profile Authorship Recognition Corpus
Efthymios Tsaprazlis, Bowen Yi, Tiantian Feng, Junghwan Kim, David Jurgens +1
Speech anonymization has focused on the acoustic signal, leaving open how much speaker information the transcribed words themselves retain. In this work, we study pairwise speaker and demographic-attribute verification from transcribed speech. We introduce SPARC (Spoken Profile Authorship Recognition Corpus), a benchmark built from two podcast corpora comprising over 12,500 speakers, 1.5M quality-filtered utterances, and speaker-level inferred or source-provided labels for sex, age, and accent, and evaluate five attribution models and three LLMs on identity- and attribute-verification trials with episode- and metadata-based topic proxies. LLM adversaries distinguish same-speaker pairs from text alone. Attribute-label agreement is harder to verify, but LLMs perform sex- and accent-label verification above chance. Finally, releasing only short probe texts (50 words) degrades the strongest adversaries the most, offering a partial reduction in observed linkage.
PDF
arXiv cs.CROct 18
Federated Learning for Malware Image Classification under Data Heterogeneity
Victor Taiwo, Cemal Nisan, Muhammad Athallah, M. Emre Gursoy, Oznur Ozkasap
Malware image classification (MIC), in which binary files are converted into visual representations and deep neural networks are trained to identify malware families, has recently emerged as an effective approach for malware detection. Federated learning (FL) enables malware image classifiers to be trained collaboratively by multiple clients without sharing raw data. However, a fundamental challenge in FL is data heterogeneity (non-IID), which is particularly relevant but understudied in the malware context. In this paper, we address this gap via three contributions. First, we present an empirical study of federated MIC under varying degrees of data heterogeneity across three popular malware image datasets (MalImg, Virus-MNIST, and MalNet). We show that while FL achieves strong accuracy under IID conditions, both accuracy and training stability degrade as data becomes increasingly non-IID. Second, we introduce a set of round-level statistics that characterize the data contributed by participating clients in each FL round, and demonstrate that class entropy (diversity of class labels present in a given round) exhibits strong positive correlation with global model accuracy. Third,…
PDF
arXiv cs.LGOct 18
EasyResearch: Honest Regression, Forecasting and Signal Classification for Researchers Who Do Not Program
Ahmad B. A. Hassanat, Ghada A. Altarawneh
EasyClassifier showed that researchers who do not program can obtain honest classification results when the correct evaluation is the default. Most applied studies, however, predict a number, forecast a series or classify recordings, and each task has its own way of producing scores that do not hold on new data. We present EasyResearch, open-source analysis cores for regression, time-series forecasting and signal classification, and EasyResearch Desktop, a Windows application that runs these three tasks and EasyClassifier's classification without code. All four follow the same rules: everything learned from data is learned on training data only, models keep their published defaults with fixed seeds, the selected model receives a separate final score, forecasts are never evaluated on shuffled data, and every run writes a report with a Methods paragraph and the references for every method used. We measured whether the reported scores are honest by keeping part of each dataset untouched. In regression (9 public datasets, 90 runs), the common practice overstated R^2 by +2.2 points and the best comparison score by +2.5, while EasyResearch's final score was -1.0; screening predictors…
PDF
arXiv cs.LGOct 18
Emergent Sparsity: How Many Effective Variables Survive Coarse-Graining in AlphaEarth Embeddings?
Johannes Hirn
AlphaEarth encodes each 10 m land pixel as a 64-component vector intended to support diverse global mapping tasks. Yet many scientific applications work at coarser spatial supports, for which fewer than 64 effective variables may suffice. We ask whether these vectors can be reorganized into ranked global nonlinear coordinates, how many suffice at a chosen reconstruction accuracy, and whether that number decreases with spatial scale. We thus describe effective dimension as a two-control surface over tolerance and spatial scale, rather than one intrinsic number. At each scale, a $β$-VAE scan with a common architecture produces a rank--distortion envelope, giving the smallest retained count achieved within the scanned family at each reconstruction tolerance. At 3% validation tolerance, this number falls from 24 to 7 when the scale is increased from 10 m to 78.9 km, whereas the corresponding PCA rank falls only from 46 to 38. Repeating the analysis on unit-norm targets preserves this trend.
PDF
arXiv cs.CVOct 18
PanoDent-KD: From Generalist Knowledge Distillation to Cross-Dataset Specialist Detection and Embedded Deployment in Panoramic Radiographs
Muhammad Waqas Ashraf, Imad Ali Shah, Ali Hassan
Reliable panoramic-radiograph detection requires consistency across datasets with different class definitions and deployment software. We present PanoDent-KD, an auditable 1280-pixel YOLO26m pipeline linking a 12-class source generalist, feature-level knowledge distillation (KD), exact classifier-row transfer, teacher-free five-class specialization, and embedded deployment. A common training and evaluation pipeline compares three source-training arms across three seeds: a supervised baseline (B1), single-teacher KD (STKD), and multi-teacher KD (MTKD). Five shared classifier rows initialize nine OralXrays-9 specialists, while the backbone, FPN-PAN neck, and dual-detection-head topology are retained unchanged. On the 2,686-image test subset, all three arms achieve macro box F1 near 0.82. B1 achieves the highest three-seed arm-level mean macro box F1 (0.8239$\pm$0.0027) and $mAP_{50:95}$ (0.6130$\pm$0.0067). STKD seed 1, selected after development but before final testing, was used for deployment. Its Jetson Orin Nano Super FP16 TensorRT engine achieves 77.03-ms median and 80.86-ms P95 prediction-call latency, throughput of 12.90 images/s, and gross total-module energy of 1.39…
PDF
arXiv cs.LGOct 18
BatchParScale: Sparse Batch-Mixing for Sequence Models
Hans Peter Lyngsøe Raaschou-jensen, M. Onurcan Kaya, Desmond Elliott
Recent test-time scaling methods improve model performance by increasing inference-time compute. One practical form of this is parallel scaling, where a model samples multiple independent reasoning streams and aggregates their answers using methods like voting, reranking, or verification. While effective, this approach leaves the streams uncoordinated, and a discovery made in one rollout cannot influence any other. Multi-Sequence Verifiers jointly score candidate answers after generation, but the reasoning streams remain independent during inference. ParScale takes a step toward model-internal parallel scaling by learning to aggregate multiple forward passes, but its streams still do not exchange information while processing a sequence. We introduce BatchParScale, an attention mechanism that allows parallel streams to exchange information through a small set of communication positions. We evaluate BatchParScale on a new Parallel Needle-in-a-Haystack retrieval benchmark and in pretraining, fine-tuning, and cooperative multi-agent reinforcement learning. Across these settings, BatchParScale outperforms ParScale on language-model loss and remains competitive on…
PDF
arXiv cs.CVOct 18
Persistent Representational Misalignment Induces Vision-Language Model Failures
Yonatan Gideoni, Yoav Gelberg, Tim G. J. Rudner, Yarin Gal
Vision-language models (VLMs) fail at some tasks that are simple for humans---but why? We hypothesize that many such failures stem from VLMs' difficulties translating between vision and language representations, a misalignment the Platonic Representation Hypothesis predicts should disappear with scale. This paper is composed of two parts: in the first, we show that existing vision and language representations are linearly unalignable. This misalignment is an inherent property of the data and hence expected to persist regardless of either scale or the alignment's complexity. In the second, we demonstrate how this misalignment both leads to a predictably induced generalization failure and correlates with existing failure modes, where more representationally aligned VLM backbones accordingly exhibit fewer failures. Overall, these results imply representations will not become aligned simply given sufficient scale, providing evidence against a strong version of the Platonic Representation Hypothesis.
PDF
arXiv cs.LGOct 18
Improving the Expressive Power of Hybrid Sequence Models via Multi-Hop Retrieval
Yam Eitan, Gilad Yehudai, Haggai Maron
Hybrid architectures offer a promising approach to efficient language modeling by combining a small number of full-attention layers with a larger number of efficient sequence layers, such as sparse attention and recurrent layers. While full-attention layers maintain a KV cache that grows linearly with sequence length, efficient layers typically rely on separate, fixed-size states rather than accessing this richer existing memory. Recent work has begun exploring ways to allow efficient layers access to the KV cache, but the theoretical benefits of such access, and the extent to which existing approaches can realize them remain poorly understood. We investigate these questions by analyzing the expressive power of individual hybrid blocks on function composition, a well-studied task in sequence-model expressivity associated with multi-hop reasoning. We first establish that both conventional hybrid blocks and those with top-$κ$ KV-cache access require $Ω(\sqrt{n})$ capacity to compute even two-function composition over a domain of size $n$. To overcome this limitation, we introduce the \emph{Multi-hop Retrieval Attention} (MuRA) hybrid block, a simple architecture that enables…
PDF
arXiv cs.CVOct 18
Visual Scaffolding: Toward Native Multimodal Reasoning
Run Shao, Zhaoyang Zhang, Ziyu Li, Linrui Xu, Ji Qi +4
The success of chain-of-thought (CoT) in complex reasoning can be attributed to a textual scaffolding effect: explicit intermediate results can be examined, reused, and composed to support subsequent reasoning, much as scaffolding supports a building under construction. However, mainstream multimodal LLMs lack an equivalent scaffold for visual distinctions that are difficult to express in concise verbal descriptions. We therefore ask: Can native visual representations become first-class citizens alongside language, providing a visual scaffold for reasoning? We define native multimodal reasoning as reasoning in which native visual representations and language jointly carry reusable intermediate states. As a concrete implementation, the visual scaffolding mechanism we proposed lets the MLLM autonomously initiate a retrieval action at any reasoning step. A lightweight retriever selects native visual features, which are then incorporated directly into the evolving CoT and remain available to subsequent steps. To evaluate this mechanism under controlled visual demands, we introduce NMR-Bench, comprising Burden Counting and Path Tracing. With 88M added parameters (approximately 2%) on…
PDF
arXiv stat.MEOct 18
Estimating Causal Bounds from Observational Data With Neural Generative Models
Max Zhu, Srivathsan Amruth, Sina Akbari, Qingyuan Zhao
Identifying causal bounds from discrete observational data is a fundamental problem in causal inference. While exact analytical bounds exist for certain graphs, this is not generally the case. In this paper, we introduce a framework for estimating such bounds using neural generative models together with a new extrapolation procedure to estimate these bounds more accurately. Across multiple causal inference settings, it produces bounds that are consistently closer to the true bounds than those obtained with existing general neural approaches. We validate the framework on a range of benchmark problems for which exact bounds are available.
PDF

Papers

Open problems across fields

General in-context learning for embodied agents1 paper raises it · 0 address it
Enables models to adapt to new tasks and environments without retraining, improving robustness in real-world deployment.
- Has GPT-6-Astra Achieved Embodied Intelligence?raises
Cost and latency in embodied control loops1 paper raises it · 0 address it
High computational and time costs limit real-time applicability of agentic systems in dynamic environments.
- Has GPT-6-Astra Achieved Embodied Intelligence?raises
Physical-state verification and failure recovery1 paper raises it · 0 address it
Agents must reliably detect and correct errors in physical interactions to avoid irreversible failures in real-world tasks.
- Has GPT-6-Astra Achieved Embodied Intelligence?raises
Long-horizon task preservation in embodied agents1 paper raises it · 0 address it
Maintaining progress over extended sequences is critical for complex, multi-step tasks in robotics and navigation.
- Has GPT-6-Astra Achieved Embodied Intelligence?raises
Open-source stacks for generalist computer-use agents1 paper raises it · 1 addresses it
Closed systems hinder reproducibility and systematic study of agent design for real-world computer tasks.
- OpenGCUA: Toward a Fully Open Stack for Generalist Computer Useraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Rising research topics

Coming with more sources: more tagged papers

Training & fine-tuning63+6200.0%
AI safety46+4500.0%
Robotics31+3000.0%
Code models23+2200.0%
Evals103+1960.0%
Image & video generation36+1100.0%
Computer vision47+1075.0%
Small LLMs11+1000.0%

Rising research topics

Ask the research

Sample

Papers

arXiv cs.CVOct 18
MotionShift: Environment-Compatible Motion Transfer via Planner-Evaluator Synergistic Adaptation
Yanchen Liu, Junyao Gao, Yanan Sun, Wensheng Chen, Guangming Lu +1
Existing motion transfer methods excel at exact, rigid motion replication from reference videos to target scenes, whereas they often fail to account for the compatibility between the transferred motion and the target scene environment in accordance with physical laws. In this work, we propose MotionShift, a novel motion transfer framework that achieves high-fidelity motion transfer while ensuring physical compatibility with the target scene. In particular, we design a planner--evaluator iterative motion adaptation mechanism, in which a Large Language Model (LLM) acts as the planner to generate motion trajectories by leveraging its strong semantic reasoning capabilities, while a Vision-Language Model (VLM) serves as the evaluator to rectify the motion based on its superior visual perception and scene understanding. Through this planner--evaluator synergistic reasoning process, the motion is adapted to the target scene in a training-free manner. The adapted motion is then used as a generative condition for an image-to-video (I2V) model to render videos in the target scene. Extensive experiments demonstrate that MotionShift achieves high-fidelity and physically compatible motion…
PDF
arXiv cs.CVOct 18
The Explainability Illusion: Must ViTs Exhibit Patch-Decoding Interpretability?
Ronen Schaffer, Hila Manor, Tomer Michaeli
Transformers are widely assumed to exhibit token-decoding explainability. In particular, in vision transformer (ViT) classifiers, decoding individual patch tokens has become a common diagnostic tool due to its tendency to yield human-interpretable outputs. In light of the increasing popularity of this approach, an important question is whether token-decoding explainability is an inherent property of transformers that should be expected to hold across architectures, scales, and training objectives, or merely an artifact of some implicit bias. In this paper we systematically study token-decoding explainability across diverse ViT settings, spanning architectures, scales, and training objectives, using both controlled experiments and real-world models. We find that while some models indeed exhibit aligned and interpretable token decodings, others exhibit either inverted explainability maps or a complete lack of correlation with the image semantics. As we show, these tendencies toward different explainability behaviors are not intrinsic to the architecture and can vary arbitrarily with changes in the optimization landscape. We provide theoretical support for these observations by…
PDF
arXiv cs.ROOct 18▲ 2
Vision as Proprioception: Estimating Humanoid Robot Pose from Video
Jiaxi Jiang, Matthias Heyrman, René Zurbrügg, Marco Hutter, Christian Holz
Estimating a humanoid robot's internal state from video has a wide range of real-world applications but remains unexplored. During interactions with a robot, its onboard state information may be unavailable due to privacy, ownership, or communication constraints. Meanwhile, online and AI-generated robot videos provide rich sources of data but typically lack corresponding joint configurations, limiting their direct use in robot learning. To address these issues, we present HumanoidPose, a new framework that treats vision as proprioception to recover full-body joint configurations in world space from video alone. Specifically, we combine pretrained human-pose features with robot kinematics in a unified model that predicts each embodiment's joint configurations. We retarget human motions to sixteen different humanoid embodiments, enabling scalable learning entirely from synthetic data. To improve real-world generalization, we further leverage unlabeled online videos through self-training to develop a 2D robot-pose detector. In our evaluation, HumanoidPose improves joint-angle and joint-position accuracy over the evaluated baselines and reduces joint-angle error by 18-32% relative to…
Code
arXiv cs.LGOct 18
A discrete-continuous-time stochastic framework for attention-deficit/hyperactivity disorder-related symptom modeling and pharmacological intervention via methylphenidate
Oana-Maria-Catalina Crisan
This paper presents an original mathematical and computational framework for modeling the efficacy of methylphenidate as an optimal control policy acting on the nonlinear dynamics of attention deficit hyperactivity disorder. Neural processes in ADHD are conceptualized as stochastic processes with trajectories that inherently converge towards stable, yet dysfunctional patterns associated with clinical symptoms. The pharmacological intervention is mathematically formalized as an external control signal that reassesses the system's drift and redirects these trajectories towards neurotypical regimes. To bridge these theoretical stochastic models with empirical clinical data, latent representations are inferred using a novel deterministic hybrid deep learning architecture, combining a one-dimensional convolutional neural network and a Vision Transformer, trained on preprocessed functional magnetic resonance imaging data.
PDF
arXiv cs.CVOct 18
Learning Lane-Structured Conditioning Fields for Online HD Mapping
Andrea Bertogalli, Anthony Dell'Eva, Marcello Ceresini, Federico Pirazzoli, Lorenzo Cipelli +3
High-definition maps provide critical structural information for downstream autonomous driving tasks. Recent methods increasingly rely on external priors to improve prediction accuracy and robustness. Yet, existing prior representations expose a trade-off: dense rasters are easy to integrate but ignore certain map geometric properties, while sparse vectors preserve geometric structure but require dedicated encoders and are difficult to plug into existing architectures. Moreover, external priors can be inaccurate, costly to acquire, or difficult to maintain, motivating a structural representation that can provide geometric guidance while remaining learnable and broadly applicable. We address this limitation with the Lane Field, a dense BEV-aligned geometric representation that encodes local lane structure at each spatial location and can be either predicted from onboard observations or constructed from external map priors. Building on this representation, we introduce a plug-and-play framework that enhances online HD mapping through two complementary mechanisms: BEV feature modulation, which injects lane-structured cues into latent BEV features, and deformable attention guidance,…
PDF
arXiv cs.LGOct 18
Data-driven forecasting of tropical cloud forest phenology: A dynamical systems and machine learning hybrid approach
Pedro Garcia, Saul Flores
Forecasting how species and ecosystems respond to climate change is a critical challenge in ecology, particularly in hyper-diverse tropical biomes. While traditional phenological models often rely on preconceived functional forms, this study introduces a data-driven hybrid approach that integrates dynamical systems theory with machine learning to forecast flowering and fruiting cycles. Using a robust 35-year dataset from a Venezuelan tropical cloud forest, we reconstruct the system's state-space using delay vectors inspired by Takens' theorem, incorporating climate forcing variables such as temperature and precipitation. The model was trained using Gaussian Process Regression, providing both point predictors and explicit uncertainty estimates. Our results clearly suggest that the synergy between dynamical systems and machine learning effectively captures the non-linear complexities of ecological time series. Specifically, the model achieved higher predictive accuracy for flowering and fruiting. This hybrid framework offers a scalable tool for anticipating phenological mismatches and informing conservation strategies in the face of global environmental change.
PDF
arXiv cs.AIOct 18
Bridging Concepts: Multi-Agent Reasoning over Scientific Concept Graphs for High-Impact Research Prediction
Donggyu Yoon, Minsung Hwang, Juneha Baek, Donghyuk Shin, Joyce Jiyoung Whang
Within a research community, new topics often emerge when previously unconnected concepts are first studied together. We construct scientific concept graphs (SCGs)--domain knowledge graphs whose nodes are fine-grained research concepts extracted from paper text by LLMs and whose edges capture their co-occurrence in papers--and study the task of forecasting high-impact concept pairs, i.e., discovering concept pairs that are currently unconnected but will have high impact when connected. To this end, we introduce new benchmark datasets constructed from CIKM, KDD, and SIGIR conference papers, with varied prediction settings, including impact forecasting for emerging concepts unseen during training. We propose MiroGraph, a Multi-agent reasoning framework with scientific concept Graphs, in which a feature designer agent designs predictive features for a given concept pair from structural, semantic, and trend perspectives, and then three LLM agents compute the actual feature values from the enclosing subgraph of the concept pair. Using these feature values, a classifier designer agent constructs a classifier that predicts the final impact labels. MiroGraph outperforms various impact…
PDF
arXiv cs.CVOct 18
Holo4D: Holistic 4D Reconstruction as Geometric Control for Video Diffusion
Yushi Lan, Zeren Jiang, Koichi Namekata, Xingang Pan, Chuanxia Zheng +1
Synthesizing a monocular video from a new camera trajectory requires preserving the observed scene geometry and motion while completing regions that become newly visible. Feed-forward 4D reconstructors recover the structure of the observed scene, whereas video diffusion models provide a generative prior for completing unseen content. We introduce Holo4D, a video reshooting framework that uses reconstructed 3D trajectories as a holistic source-view 4D scaffold. We project these trajectories into the requested views and encode their geometry and source appearance to guide a pretrained video diffusion model. Together with the source video and target cameras, the scaffold grounds generation in reconstructed observations while leaving unsupported regions to the generative prior. Experiments demonstrate the value of trajectory-based conditioning for camera control and novel-view synthesis. The framework accommodates different 4D reconstructors without retraining the video generator, allowing it to benefit from future advances in source reconstruction. More details can be found in our project page.
PDF
arXiv cs.CVOct 18
GeoART: Geometry-Aware Refinement via Test-Time Scaling for Camera-Conditioned Video Diffusion
Liudi Yang, Ziyuan Liu
Camera-conditioned video diffusion models often suffer from inaccurate camera control and geometric inconsisten- cies because camera constraints and estimated geometry are only weakly enforced during denoising. Existing reme- dies often require costly geometry-aware fine-tuning or ad- ditional 3D supervision. We introduce GeoART, a training- free self-refinement framework that improves camera con- trollability through geometry-aware test-time scaling. At selected denoising steps, GeoART generates multiple can- didates within the Predict-and-Perturb cycle and eval- uates them using a geometry prior, without directly modify- ing the denoising trajectory. A confidence gate suppresses unreliable geometric evidence, while rank-calibrated prob- abilistic selection combines score magnitude and relative rank to choose the next refinement state. Experiments demonstrate consistent improvements in camera controlla- bility, multi-view consistency, and visual quality over exist- ing sampling and self-refinement methods, without training or modifying the pretrained video diffusion model
PDF
arXiv cs.LGOct 18
EG-GRPO: Evidence-Guided Step-level Credit Assignment for Deep Search Agents
Sijia Luo, Mengjie Gao, Yuxiao He, Mengshu Sun, Cuiping Li +2
LLM-based search agents demonstrate strong capabilities in long-horizon information seeking and reasoning, typically trained via reinforcement learning. However, existing approaches predominantly rely on trajectory-level outcome rewards, providing limited supervision for complex search and reasoning processes. Although step-level credit assignment offers a promising solution, obtaining reliable and task-grounded supervision for open-ended search remains challenging. In this paper, we propose Evidence-Guided Group Relative Policy Optimization (EG-GRPO), a framework that derives step-level supervision from the evidence annotations available in synthetic deep search data. EG-GRPO identifies the first supporting citation for each required evidence claim and uses the newly acquired evidence to construct step-level process rewards. By representing the accumulated evidence as an evolving knowledge state, EG-GRPO further performs state-conditioned relative advantage estimation and combines the resulting step-level signal with the standard trajectory-level outcome advantage. Experiments on five challenging deep search benchmarks show that EG-GRPO generally outperforms standard GRPO and…
PDF
arXiv cs.CLOct 18▲ 4
SPARC: Spoken Profile Authorship Recognition Corpus
Efthymios Tsaprazlis, Bowen Yi, Tiantian Feng, Junghwan Kim, David Jurgens +1
Speech anonymization has focused on the acoustic signal, leaving open how much speaker information the transcribed words themselves retain. In this work, we study pairwise speaker and demographic-attribute verification from transcribed speech. We introduce SPARC (Spoken Profile Authorship Recognition Corpus), a benchmark built from two podcast corpora comprising over 12,500 speakers, 1.5M quality-filtered utterances, and speaker-level inferred or source-provided labels for sex, age, and accent, and evaluate five attribution models and three LLMs on identity- and attribute-verification trials with episode- and metadata-based topic proxies. LLM adversaries distinguish same-speaker pairs from text alone. Attribute-label agreement is harder to verify, but LLMs perform sex- and accent-label verification above chance. Finally, releasing only short probe texts (50 words) degrades the strongest adversaries the most, offering a partial reduction in observed linkage.
PDF
arXiv cs.CROct 18
Federated Learning for Malware Image Classification under Data Heterogeneity
Victor Taiwo, Cemal Nisan, Muhammad Athallah, M. Emre Gursoy, Oznur Ozkasap
Malware image classification (MIC), in which binary files are converted into visual representations and deep neural networks are trained to identify malware families, has recently emerged as an effective approach for malware detection. Federated learning (FL) enables malware image classifiers to be trained collaboratively by multiple clients without sharing raw data. However, a fundamental challenge in FL is data heterogeneity (non-IID), which is particularly relevant but understudied in the malware context. In this paper, we address this gap via three contributions. First, we present an empirical study of federated MIC under varying degrees of data heterogeneity across three popular malware image datasets (MalImg, Virus-MNIST, and MalNet). We show that while FL achieves strong accuracy under IID conditions, both accuracy and training stability degrade as data becomes increasingly non-IID. Second, we introduce a set of round-level statistics that characterize the data contributed by participating clients in each FL round, and demonstrate that class entropy (diversity of class labels present in a given round) exhibits strong positive correlation with global model accuracy. Third,…
PDF
arXiv cs.LGOct 18
EasyResearch: Honest Regression, Forecasting and Signal Classification for Researchers Who Do Not Program
Ahmad B. A. Hassanat, Ghada A. Altarawneh
EasyClassifier showed that researchers who do not program can obtain honest classification results when the correct evaluation is the default. Most applied studies, however, predict a number, forecast a series or classify recordings, and each task has its own way of producing scores that do not hold on new data. We present EasyResearch, open-source analysis cores for regression, time-series forecasting and signal classification, and EasyResearch Desktop, a Windows application that runs these three tasks and EasyClassifier's classification without code. All four follow the same rules: everything learned from data is learned on training data only, models keep their published defaults with fixed seeds, the selected model receives a separate final score, forecasts are never evaluated on shuffled data, and every run writes a report with a Methods paragraph and the references for every method used. We measured whether the reported scores are honest by keeping part of each dataset untouched. In regression (9 public datasets, 90 runs), the common practice overstated R^2 by +2.2 points and the best comparison score by +2.5, while EasyResearch's final score was -1.0; screening predictors…
PDF
arXiv cs.LGOct 18
Emergent Sparsity: How Many Effective Variables Survive Coarse-Graining in AlphaEarth Embeddings?
Johannes Hirn
AlphaEarth encodes each 10 m land pixel as a 64-component vector intended to support diverse global mapping tasks. Yet many scientific applications work at coarser spatial supports, for which fewer than 64 effective variables may suffice. We ask whether these vectors can be reorganized into ranked global nonlinear coordinates, how many suffice at a chosen reconstruction accuracy, and whether that number decreases with spatial scale. We thus describe effective dimension as a two-control surface over tolerance and spatial scale, rather than one intrinsic number. At each scale, a $β$-VAE scan with a common architecture produces a rank--distortion envelope, giving the smallest retained count achieved within the scanned family at each reconstruction tolerance. At 3% validation tolerance, this number falls from 24 to 7 when the scale is increased from 10 m to 78.9 km, whereas the corresponding PCA rank falls only from 46 to 38. Repeating the analysis on unit-norm targets preserves this trend.
PDF
arXiv cs.CVOct 18
PanoDent-KD: From Generalist Knowledge Distillation to Cross-Dataset Specialist Detection and Embedded Deployment in Panoramic Radiographs
Muhammad Waqas Ashraf, Imad Ali Shah, Ali Hassan
Reliable panoramic-radiograph detection requires consistency across datasets with different class definitions and deployment software. We present PanoDent-KD, an auditable 1280-pixel YOLO26m pipeline linking a 12-class source generalist, feature-level knowledge distillation (KD), exact classifier-row transfer, teacher-free five-class specialization, and embedded deployment. A common training and evaluation pipeline compares three source-training arms across three seeds: a supervised baseline (B1), single-teacher KD (STKD), and multi-teacher KD (MTKD). Five shared classifier rows initialize nine OralXrays-9 specialists, while the backbone, FPN-PAN neck, and dual-detection-head topology are retained unchanged. On the 2,686-image test subset, all three arms achieve macro box F1 near 0.82. B1 achieves the highest three-seed arm-level mean macro box F1 (0.8239$\pm$0.0027) and $mAP_{50:95}$ (0.6130$\pm$0.0067). STKD seed 1, selected after development but before final testing, was used for deployment. Its Jetson Orin Nano Super FP16 TensorRT engine achieves 77.03-ms median and 80.86-ms P95 prediction-call latency, throughput of 12.90 images/s, and gross total-module energy of 1.39…
PDF
arXiv cs.LGOct 18
BatchParScale: Sparse Batch-Mixing for Sequence Models
Hans Peter Lyngsøe Raaschou-jensen, M. Onurcan Kaya, Desmond Elliott
Recent test-time scaling methods improve model performance by increasing inference-time compute. One practical form of this is parallel scaling, where a model samples multiple independent reasoning streams and aggregates their answers using methods like voting, reranking, or verification. While effective, this approach leaves the streams uncoordinated, and a discovery made in one rollout cannot influence any other. Multi-Sequence Verifiers jointly score candidate answers after generation, but the reasoning streams remain independent during inference. ParScale takes a step toward model-internal parallel scaling by learning to aggregate multiple forward passes, but its streams still do not exchange information while processing a sequence. We introduce BatchParScale, an attention mechanism that allows parallel streams to exchange information through a small set of communication positions. We evaluate BatchParScale on a new Parallel Needle-in-a-Haystack retrieval benchmark and in pretraining, fine-tuning, and cooperative multi-agent reinforcement learning. Across these settings, BatchParScale outperforms ParScale on language-model loss and remains competitive on…
PDF
arXiv cs.CVOct 18
Persistent Representational Misalignment Induces Vision-Language Model Failures
Yonatan Gideoni, Yoav Gelberg, Tim G. J. Rudner, Yarin Gal
Vision-language models (VLMs) fail at some tasks that are simple for humans---but why? We hypothesize that many such failures stem from VLMs' difficulties translating between vision and language representations, a misalignment the Platonic Representation Hypothesis predicts should disappear with scale. This paper is composed of two parts: in the first, we show that existing vision and language representations are linearly unalignable. This misalignment is an inherent property of the data and hence expected to persist regardless of either scale or the alignment's complexity. In the second, we demonstrate how this misalignment both leads to a predictably induced generalization failure and correlates with existing failure modes, where more representationally aligned VLM backbones accordingly exhibit fewer failures. Overall, these results imply representations will not become aligned simply given sufficient scale, providing evidence against a strong version of the Platonic Representation Hypothesis.
PDF
arXiv cs.LGOct 18
Improving the Expressive Power of Hybrid Sequence Models via Multi-Hop Retrieval
Yam Eitan, Gilad Yehudai, Haggai Maron
Hybrid architectures offer a promising approach to efficient language modeling by combining a small number of full-attention layers with a larger number of efficient sequence layers, such as sparse attention and recurrent layers. While full-attention layers maintain a KV cache that grows linearly with sequence length, efficient layers typically rely on separate, fixed-size states rather than accessing this richer existing memory. Recent work has begun exploring ways to allow efficient layers access to the KV cache, but the theoretical benefits of such access, and the extent to which existing approaches can realize them remain poorly understood. We investigate these questions by analyzing the expressive power of individual hybrid blocks on function composition, a well-studied task in sequence-model expressivity associated with multi-hop reasoning. We first establish that both conventional hybrid blocks and those with top-$κ$ KV-cache access require $Ω(\sqrt{n})$ capacity to compute even two-function composition over a domain of size $n$. To overcome this limitation, we introduce the \emph{Multi-hop Retrieval Attention} (MuRA) hybrid block, a simple architecture that enables…
PDF
arXiv cs.CVOct 18
Visual Scaffolding: Toward Native Multimodal Reasoning
Run Shao, Zhaoyang Zhang, Ziyu Li, Linrui Xu, Ji Qi +4
The success of chain-of-thought (CoT) in complex reasoning can be attributed to a textual scaffolding effect: explicit intermediate results can be examined, reused, and composed to support subsequent reasoning, much as scaffolding supports a building under construction. However, mainstream multimodal LLMs lack an equivalent scaffold for visual distinctions that are difficult to express in concise verbal descriptions. We therefore ask: Can native visual representations become first-class citizens alongside language, providing a visual scaffold for reasoning? We define native multimodal reasoning as reasoning in which native visual representations and language jointly carry reusable intermediate states. As a concrete implementation, the visual scaffolding mechanism we proposed lets the MLLM autonomously initiate a retrieval action at any reasoning step. A lightweight retriever selects native visual features, which are then incorporated directly into the evolving CoT and remain available to subsequent steps. To evaluate this mechanism under controlled visual demands, we introduce NMR-Bench, comprising Burden Counting and Path Tracing. With 88M added parameters (approximately 2%) on…
PDF
arXiv stat.MEOct 18
Estimating Causal Bounds from Observational Data With Neural Generative Models
Max Zhu, Srivathsan Amruth, Sina Akbari, Qingyuan Zhao
Identifying causal bounds from discrete observational data is a fundamental problem in causal inference. While exact analytical bounds exist for certain graphs, this is not generally the case. In this paper, we introduce a framework for estimating such bounds using neural generative models together with a new extrapolation procedure to estimate these bounds more accurately. Across multiple causal inference settings, it produces bounds that are consistently closer to the true bounds than those obtained with existing general neural approaches. We validate the framework on a range of benchmark problems for which exact bounds are available.
PDF