50 citations · 122 across the 16 of their papers we have counts for
7 papers · 1 filter
C3: Rethinking Process Supervision via Confidence-Guided Credit Correction in Multi-Turn Reinforcement Learning
Ai Jian, Haoran Pan, Eryu Guo +5
Large language models are increasingly trained as multi-turn agents that interact with external tools. However, outcome-only reinforcement learning can produce a form of misguided…
hacktrace: behavior-supervised detection of reward hacking during code generation
Hao Jiang, Xin Li, Annan Wang +2
A coding agent can earn a passing grade by fixing its code, or by deleting the test that exposes the bug. Detecting such reward hacking requires recognizing attempted shortcuts, in…
Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation
Xin Li, Hao Jiang, Xin Gao +6
Reinforcement learning can turn one language model into several specialists, each excellent at a single skill such as mathematics, coding or following instructions, but users need…
PRISMR: Overcoming Parse Collapse in Multimodal Listwise Ranking via Parameterized Representation Internalization
Hao Jiang, Xin Li, Annan Wang +4
Generative listwise ranking with Large Multimodal Models (LMMs) aims to capture global list context in a single forward pass, but its effectiveness degrades in long-context multimo…
OmniInteract: Benchmarking Real-World Streaming Interaction for Real-Time Omnimodal Assistants
Xudong Lu, Xueying Li, Annan Wang +8
We introduce OmniInteract, a streaming benchmark for real-time omnimodal large language models evaluated through native online inference over audio-visual streams. Unlike offline v…
ErrOPD: When Does On-Policy Distillation Transfer Teacher Errors?
Xin Li, Hao Jiang, Annan Wang +2
A distilled student can copy its teacher's mistakes along with its skills. On-policy distillation (OPD), used in recent post-training recipes, has the teacher grade every token of…
RLPO: Residual Listwise Preference Optimization for Long-Context Review Ranking
Hao Jiang, Zhi Yang, Annan Wang +2
Review ranking is pivotal in e-commerce for prioritizing diagnostic and authentic feedback from the deluge of user-generated content. While large language models have improved sema…