5 papers
Guidance Contrastive Token Credit Assignment for Discrete Policy Optimization
Shufan Li, Konstantinos Kallidromitis, Akash Gokul +2
Group-advantage-based reinforcement learning methods, such as GRPO and DAPO, have demonstrated strong performance across diverse domains, including mathematical reasoning and text-…
LongCodeBench: Evaluating Coding LLMs at 1M Context Windows
Stefano Rando, Luca Romani, Alessio Sampieri +5
Context lengths for models have grown rapidly, from thousands to millions of tokens in just a few years. The extreme context sizes of modern long-context models have made it diffic…
UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generation
Chaitanya Patel, Hiroki Nakamura, Yuta Kyuragi +3
Egocentric human motion generation and forecasting with scene-context is crucial for enhancing AR/VR experiences, improving human-robot interaction, advancing assistive technologie…
VideoMultiAgents: A Multi-Agent Framework for Video Question Answering
Noriyuki Kugo, Xiang Li, Zixin Li +9
Video Question Answering (VQA) inherently relies on multimodal reasoning, integrating visual, temporal, and linguistic cues to achieve a deeper understanding of video content. Howe…
Few-Shot Classification of Interactive Activities of Daily Living (InteractADL)
Zane Durante, Robathan Harries, Edward Vendrow +5
Understanding Activities of Daily Living (ADLs) is a crucial step for different applications including assistive robots, smart homes, and healthcare. However, to date, few benchmar…