14 papers
RRPO: Reference-Relative Policy Optimization with Stratified Conditional Rollouts
Yuxin Xiong, Xunyi Jiang, Rohan Surana +8
Group Relative Policy Optimization (GRPO) has shown strong effectiveness in reinforcement learning from verifiable feedback, where sampled rollouts can be compared within a group u…
Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering
Sheldon Yu, Tong Yu, Xunyi Jiang +6
Extended reasoning has become standard for frontier Large Language Models (LLMs), yet the trajectories these models produce remain largely uncontrollable. Existing methods for shap…
F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking
Rohan Surana, Gagan Mundada, Junda Wu +9
Traditional retrieval pipelines optimize utility through stages of candidate retrieval and reranking, where ranking operates over a predefined candidate set. Large Language Models…
MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization
Rohan Surana, Xintong Li, Sheldon Yu +7
Multi-negative preference optimization under the Plackett--Luce (PL) model extends Direct Preference Optimization (DPO) by leveraging comparative signals across one preferred and m…
Skill-R1: Agent Skill Evolution via Reinforcement Learning
Yash Vishe, Rohan Surana, Xunyi Jiang +8
Agentic large language models often rely on skills, reusable natural language procedures that guide planning, action, and tool use. In practice, skills are typically improved throu…
Skill-CMIB: Multimodal Agent Skill for Consistent Action via Conditional Multimodal Information Bottleneck
Zihan Huang, Junda Wu, Tong Yu +6
While LLM-based agents excel at planning and executing long action sequences, their execution often remains inconsistent across trials, limiting reliability. Consolidating agent co…
Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning
Rohan Surana, Gagan Mundada, Xunyi Jiang +19
Reinforcement learning (RL) has become a central post-training tool for improving the reasoning abilities of large language models (LLMs). In these systems, the rollout, the trajec…
WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning
Gagan Mundada, Zihan Huang, Rohan Surana +8
Group Relative Policy Optimization (GRPO) is effective for training language models on complex reasoning. However, since the objective is defined relative to a group of sampled tra…
AMPS: Adaptive Modality Preference Steering via Functional Entropy
Zihan Huang, Xintong Li, Rohan Surana +5
Multimodal Large Language Models (MLLMs) often exhibit significant modality preference, which is a tendency to favor one modality over another. Depending on the input, they may ove…
Evaluation on Entity Matching in Recommender Systems
Zihan Huang, Rohan Surana, Zhouhang Xie +3
Entity matching is a crucial component in various recommender systems, including conversational recommender systems (CRS) and knowledge-based recommender systems. However, the lack…
Importance Sampling for Multi-Negative Multimodal Direct Preference Optimization
Xintong Li, Chuhan Wang, Junda Wu +4
Direct Preference Optimization (DPO) has recently been extended from text-only models to vision-language models. However, existing methods rely on oversimplified pairwise compariso…
MusiCRS: Benchmarking Audio-Centric Conversational Recommendation
Rohan Surana, Amit Namburi, Gagan Mundada +4
Conversational recommendation has advanced rapidly with large language models (LLMs), yet music remains a uniquely challenging domain in which effective recommendations require rea…
In-context Ranking Preference Optimization
Junda Wu, Rohan Surana, Zhouhang Xie +6
Recent developments in Direct Preference Optimization (DPO) allow large language models (LLMs) to function as implicit ranking models by maximizing the margin between preferred and…
Interacting Chern insulator transition on the sphere: revealing the Gross-Neveu-Yukawa criticality
Zhi-Qiang Gao, Taige Wang, Dung-Hai Lee
In two spatial dimensions, the transition between topological and trivial Chern insulators exemplifies a class of beyond-Landau critical phenomena. We show that the interaction-dri…