PhysVista is a new benchmark that evaluates physical intelligence in Vision‑Language Models (VLMs) by integrating perception, reasoning, and plausibility assessment into a closed cognitive loop. It distinguishes between event‑level and scale‑level reasoning and tests models on both real‑world and AI‑generated videos to provide a holistic, fine‑grained analysis of physical understanding. Experiments show significant gaps in VLMs’ physical reasoning and plausibility assessment, underscoring the need for more principled, physically grounded multimodal designs.
By Xinge Peng, Yiting Lu, Tianwu Zhi, Wen Wen, Jianzhao Liu, Xin Li, Zhibo Chen
arXiv:2610.00661v1 Announce Type: cross
Abstract: Diffusion large language models (dLLMs) generate text by denoising a sequence or successive blocks, allowing several tokens to be revealed in paralle...
By Yue YU, Bowen Zuo, David Crandall, Yinglun Zhu, Dongruo Zhou
arXiv:2610.00391v1 Announce Type: cross
Abstract: Synthetic medical tabular data generation has become essential for developing and validating computer-based medical systems (CBMSs) when real clinica...
By Michael Vasilakakis (Department of Computer Science and Biomedical Informatics, University of Thessaly, Lamia, Greece), Dimitris K. Iakovidis (Department of Computer Science and Biomedical Informatics, University of Thessaly, Lamia, Greece)
arXiv:2610.01352v1 Announce Type: new
Abstract: Open multimodal reasoning models have benefited from large-scale reasoning supervision, yet reliable post-training remains challenging due to uneven da...
By Juekai Lin, Honglin Lin, Yuqian Yuan, Xiaolong Wu, Jie Cao, Liang Liang, Yunqi Cao, Yun Zhu, Wenqiao Zhang, Lijun Wu
High-fidelity solubility prediction is fundamental to pharmaceutical development and environmental partitioning, where accurate modeling must couple molecular structure with thermodynamic behavior acr...
The ability of vision-language models (VLMs) to associate visual identities with biographical information creates a need for selective unlearning of personally identifiable information (PII) while pre...
Dynamic resource assignment, the real-time allocation of task streams to heterogeneous processing nodes, is the backbone of modern computing infrastructure. While learning-based schedulers excel in re...
The article titled "Autoencoders vs. PCA: I Rigged the Test and PCA Still Won" discusses a comparative study between autoencoders and Principal Component Analysis (PCA). It highlights that a theoretical advantage claimed for autoencoders did not hold up when tested against a real benchmark, leading to PCA outperforming the autoencoder in this scenario.
By Himanshu Sharma
Adaptive model search is path dependent: once a challenger is adopted, it becomes the reference from which later candidates are generated. A statistically unsupported replacement can therefore alter h...
Existing image forgery detectors often suffer from generalization to unseen manipulation methods due to the limited ability to capture transferable forensic cues. Recent cross-reconstruction based met...
Open multimodal reasoning models have benefited from large-scale reasoning supervision, yet reliable post-training remains challenging due to uneven data quality, inefficient supervision construction,...
LLM arenas turn pairwise human preferences into model rankings. Those preferences may reflect how an answer is presented as well as what it says. We take a stylometric approach to 137,293 decisive Fre...
As the capabilities and ubiquity of Large Language Models (LLMs) grow, so does their environmental footprint. Despite calls for responsible AI, the machine learning community lacks standardised practi...
The paper introduces Rita, a reinforcement learning framework that addresses thinking drift in vision‑language models by enforcing consistency between reasoning and answers. Rita employs two reasoning‑label‑free rewards—thinking and consistency rewards—derived from the conditional probability of reference answers, and uses a difficulty‑aware data filtering strategy to select informative samples for training. Experiments on EgoIntention and RefEgo‑Int benchmarks demonstrate that Rita outperforms both supervised fine‑tuning and vanilla RL‑fine‑tuned approaches.
By Pengzhan Sun, Shiu-hong Kao, Shijie Li, Yongyi Su, Junbin Xiao, Arjun Reddy Akula, Angela Yao
The paper proposes a new matrix multiplication approach called SFC-CA GEMM that uses space‑filling curves to partition work in a platform‑ and shape‑oblivious way, achieving communication‑avoiding properties. It demonstrates provable asymptotic communication optimality for both square and rectangular matrices and outperforms vendor libraries on multiple x86 and Arm platforms, with speedups up to 5.5× for specific shapes and 1.8× in weighted harmonic mean throughput. The method is applied to real‑world tasks, improving large‑language‑model inference by up to 1.85× and distributed‑memory GEMM by up to 2.3× over state‑of‑the‑art frameworks.
By Evangelos Georganas, Alexander Heinecke, Pradeep Dubey
This paper introduces IDEAL, a framework for few-shot anomaly detection that uses both normal and anomalous reference examples. IDEAL suppresses irrelevant normal variations and encodes intrinsic deviation vectors that capture discriminative anomaly directions. Experiments on eight real-world datasets show that IDEAL generalizes to unseen anomalies and outperforms existing methods.
By Huan Wang, Jun Shen, Jun Yan, Guansong Pang
arXiv:2605.18727v2 Announce Type: replace-cross
Abstract: Evaluating embodied systems with real dexterous hardware requires more than isolated motor-skill tests: an agent must perceive a changing sce...
By Feng Chen, Tianzhe Chu, Li Sun, Pei Zhou, Zhuxiu Xu, Shenghua Gao, Yuexiang Zhai, Yanchao Yang, Yi Ma
DiDA introduces a lightweight video object segmentation framework that leverages Distillation Learning of Deformable Attention. The method uses deformable attention to adapt key and value positions across frames, enabling object representations that are responsive to spatial and temporal changes. Experiments on DAVIS and YouTube‑VOS benchmarks show state‑of‑the‑art performance and efficient memory usage.
By Quang-Trung Truong, Duc Thanh Nguyen, Binh-Son Hua, Sai-Kit Yeung
The paper introduces TSDA-Track, a Template-Search Domain Adaptation framework designed to reduce modality gaps in cross‑modal visual object tracking. Two variants are explored: Pre‑AFA TSDA‑Track uses adversarial alignment before transformer interaction, while Enc‑CFA TSDA‑Track applies contrastive alignment after interaction to strengthen cross‑modal correspondence. Experiments on datasets such as LasHeR, RGBT234, GTOT, and Anti‑UAV‑024 show that both variants outperform state‑of‑the‑art trackers, with Pre‑AFA achieving an SR/PR of 43.2/56.0 on RGBT234 under the modality‑switch protocol.
By Fereshteh Aghaee Meibodi, Amir Mehdi Soufi Enayati, Shadi Alijani, Homayoun Najjaran
RealWorldShop introduces a new benchmark for conversational shopping agents, featuring 3.28 million grounded products, structured shopping episodes, a profile‑grounded user simulator, and role‑play evaluation. Analysis reveals that existing systems generate locally plausible responses but struggle with state tracking, constraint updating, and grounded convergence, especially in ambiguous or multi‑intent scenarios. The authors propose REALSHOP_AGENT, a session‑control framework with explicit state management, shopping‑flow control, catalog‑grounded retrieval, and runtime guards, which consistently outperforms strong baselines on the benchmark.
By Xinwei Yang, Kelong Mao, Yudong Guo, Sulong Xu, Simiu Gu, Chen Huang, Wenqiang Lei