We present an efficient method to distill reasoning capabilities into compact video-language models (VLMs) for video question answering (VideoQA). Our approach fine-tunes a 2B-parameter model using only $\sim$900 uncertainty-selected examples, each augmented with synthetic chain-of-thought (CoT) rationales generated by...
Mantek Singh, Jeshwanth Challagundla, Siddharth Raina et al.· Conference on Multimedia Mod...· 0 citations
PaintCopilot lets AI autonomously act on an artwork whose direction is still open, through interruptible, revisable delegation mechanisms spanning individual strokes, extended sequences, bounded regions, and prior stroke history.
MedVA is presented, an end-to-end neuro-symbolic agentic system for medical volume visualization that addresses limitations through three complementary agents and provides more complete, clinically grounded ROI specifications than MLLM-only reasoning.
Haill An, Suhyeon Kim, Min-Jun Kang et al.· 0 citations
Most knowledge of graphical perception comes from behavioral studies. Understanding from a neural perspective is much more limited due in part to neuroimaging studies'expensiveness and difficulty to conduct. In this paper, we evaluate whether Meta's Tribe V2 neural encoding model can recover neural contrasts from a vis...
Erfan Nasirzadeh Orang, Zack While· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Congruency Score (CS), a lightweight calibration layer that maps image--text similarity evidence into a bounded score, is proposed, establishing long-text image--text congruence scoring as a calibrated score-estimation problem, where retrieval performance, human association, and threshold calibration must be evaluated...
Long-video understanding remains challenging for multimodal large language models (MLLMs) because densely encoding long frame sequences is computationally expensive, while uniform sampling under a limited visual budget can miss sparse yet decisive evidence. Recent training-free keyframe selection methods have enabled m...
Hongchang Shi, Jin-Peng Hu, Ao Wang et al.· 1 citation
Robots need touch to manipulate objects safely and reliably, as many properties, such as softness, texture, and contact stability, are hard to infer from vision alone. However, vision-based tactile sensors yield different observations of the same material due to variations in optics, elastomer properties, and illuminat...
Mashood M. Mohsan, Muhayy Ud Din, Binzhao Xu et al.· 0 citations
The results indicate that structured temporal representations can support both performance and inspectability by preserving symbolic structure, capturing temporal continuity, and providing human-readable diagnostics for video reasoning.
Reimplementation of the challenge evaluator shows that its BLEU-4 and METEOR are local variants whose F-mean weights recall nine to one, that two clinicians agree on 47 percent of findings for the same patient, and that a constant report consequently outscores a genuine second clinician report by 0.165 captioning.
A. B. George, Govind Arun, S. N. Krishna et al.· 0 citations
Maxillofacial report generation from cone beam computed tomography is scored here by a composite objective placing 80% of its weight on a large language model judgement of factual entailment and 20% on lexical overlap, of which only the lexical fifth is visible during development. The grader's BLEU-4 and METEOR routine...
A. B. George, Govind Arun, S. N. Krishna et al.· 0 citations
PhysMent is introduced, a benchmark that evaluates LLM physical reasoning via iterative, toolmediated interaction with a MuJoCo physics simulator, and results show that current models perform reasonably well on qualitative single-concept tasks but degrade substantially on quantitative tasks that demand precise, multi-s...
Joseph Chan, Utkarsh Jha, Xi-Yin Yang et al.· 0 citations
This paper proposes a training paradigm where Mode Seeking meets Mean Seeking, decoupling local fidelity from long-term coherence based on a unified representation via a Decoupled Diffusion Transformer, and closes the fidelity-horizon gap by jointly improving local sharpness, motion and long-range consistency.
Shengqu Cai, Weili Nie, Chao Liu et al.· arXiv.org· 12 citations· ⚡2
Exploring how generative AI could make machine vision more accessible to businesses. The post GenEye in a Box: Making Machine Vision Something You Can Just Ask For appeared first on GPT-Lab.
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
Computer scientist, entrepreneur, and philanthropist will collaborate with the MIT Schwarzman College of Computing to advance AI and scientific discovery.
