2 papers
cs.CL2026
LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical Supervision
Jundong Xu, Hao Fei, Huichi Zhou +6
Although LLMs exhibit strong reasoning capabilities, existing training methods largely depend on outcome-based feedback, which can produce correct answers with flawed reasoning. Pr…
cs.CV2025
UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalist
Zhengyang Liang, Daoan Zhang, Huichi Zhou +8
While specialized AI models excel at isolated video tasks like generation or understanding, real-world applications demand complex, iterative workflows that combine these capabilit…