From the 1 of 8 linked papers with an AI index.
8 papers
Beyond Chain-of-Thought: Rewrite as a Universal Interface for Generative Multimodal Embeddings
Peixi Wu, Ke Mei, Feipeng Ma +15
The paper introduces RIME, a rewrite-driven framework that improves multimodal embeddings by jointly optimizing generation and retrieval-friendly rewriting, aligning generative and…
From Generic Correlation to Input-Specific Credit in On-Policy Self Distillation
Guobin Shen, Lei Huang, Xiang Cheng +4
On-policy self-distillation has emerged as a promising paradigm for post-training language models, in which the model conditions on environment feedback to serve as its own teacher…
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
Guobin Shen, Xiang Cheng, Chenxiao Zhao +4
On-policy self-distillation, where a student is pulled toward a copy of itself conditioned on privileged context (e.g., a verified solution or feedback), offers a promising directi…
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
Guobin Shen, Chenxiao Zhao, Xiang Cheng +2
Off-policy updates are inevitable in reinforcement learning (RL) for large language models (LLMs) due to rollout staleness from asynchronous training and mismatches between trainin…
DeepEyesV2: Toward Agentic Multimodal Model
Jack Hong, Chenxiao Zhao, ChengLin Zhu +3
Agentic multimodal models should not only comprehend text and images, but also actively invoke external tools, such as code execution environments and web search, and integrate the…
Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning
Lei Huang, Xiang Cheng, Chenxiao Zhao +6
Large language models (LLMs) typically receive diverse natural language (NL) feedback through interaction with the environment. However, current reinforcement learning (RL) algorit…