4 citations · 6 across the 29 of their papers we have counts for
29 papers
Kimi K3: Open Frontier Intelligence
Kimi Team, Tongtong Bai, Yifan Bai +398
We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token context window. Kimi K3 is…
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…
Process Reward Informed Tree Rollout for Effective Multi-Turn RL
Xintong Li, Sha Li, Yuwei Zhang +8
Reinforcement learning (RL) has become a key approach for training LLM agents, yet popular methods such as GRPO/RLOO rely on multiple independently sampled complete trajectories fo…
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…
Learning with Rare Success but Rich Feedback via Reflection-Enhanced Self-Distillation
Yuwei Zhang, Sha Li, Changlong Yu +9
Enabling Large Language Models (LLMs) to continuously improve from environmental interactions is a central challenge in post-training. While on-policy self-distillation offers a pr…
OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct Agents
Sheldon Yu, Junda Wu, Xintong Li +6
Large language model agents interleave reasoning, action selection, and observation to solve sequential decision-making tasks. In deployed settings where agents repeatedly handle r…
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…
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…
Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning
Xintong Li, Sha Li, Rongmei Lin +10
Large reasoning models improve with more test-time computation, but often overthink, producing unnecessarily long chains-of-thought that raise cost without improving accuracy. Prio…
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…
SceneAlign: Aligning Multimodal Reasoning to Scene Graphs in Complex Visual Scenes
Chuhan Wang, Xintong Li, Jennifer Yuntong Zhang +5
Multimodal large language models often struggle with faithful reasoning in complex visual scenes, where intricate entities and relations require precise visual grounding at each st…
EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning
Chuanrui Hu, Xingze Gao, Zuyi Zhou +8
Large Language Models (LLMs) are increasingly deployed as long-term interactive agents, yet their limited context windows make it difficult to sustain coherent behavior over extend…
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…
Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics
Sheldon Yu, Yuxin Xiong, Junda Wu +6
Recent advances in chain-of-thought (CoT) prompting have enabled large language models (LLMs) to perform multi-step reasoning. However, the explainability of such reasoning remains…
CTRLS: Chain-of-Thought Reasoning via Latent State-Transition
Junda Wu, Yuxin Xiong, Xintong Li +7
Chain-of-thought (CoT) reasoning enables large language models (LLMs) to break down complex problems into interpretable intermediate steps, significantly enhancing model transparen…
A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models
Zhouhang Xie, Junda Wu, Yiran Shen +9
Personalized preference alignment for large language models (LLMs), the process of tailoring LLMs to individual users' preferences, is an emerging research direction spanning the a…
ASRL:A robust loss function with potential for development
Chenyu Hui, Anran Zhang, Xintong Li
In this article, we proposed a partition:wise robust loss function based on the previous robust loss function. The characteristics of this loss function are that it achieves high r…
Toward Multi-Session Personalized Conversation: A Large-Scale Dataset and Hierarchical Tree Framework for Implicit Reasoning
Xintong Li, Jalend Bantupalli, Ria Dharmani +2
There has been a surge in the use of large language models (LLM) conversational agents to generate responses based on long-term history from multiple sessions. However, existing lo…
Active Learning for Direct Preference Optimization
Branislav Kveton, Xintong Li, Julian McAuley +4
Direct preference optimization (DPO) is a form of reinforcement learning from human feedback (RLHF) where the policy is learned directly from preferential feedback. Although many m…
From Selection to Generation: A Survey of LLM-based Active Learning
Yu Xia, Subhojyoti Mukherjee, Zhouhang Xie +31
Active Learning (AL) has been a powerful paradigm for improving model efficiency and performance by selecting the most informative data points for labeling and training. In recent…
Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent
Junda Wu, Yuxin Xiong, Xintong Li +9
Recent MLLMs have shown emerging visual understanding and reasoning abilities after being pre-trained on large-scale multimodal datasets. Unlike pre-training, where MLLMs receive r…
GUI Agents: A Survey
Dang Nguyen, Jian Chen, Yu Wang +27
Graphical User Interface (GUI) agents, powered by Large Foundation Models, have emerged as a transformative approach to automating human-computer interaction. These agents autonomo…