4 citations · 16 across the 48 of their papers we have counts for
15 papers · 1 filter
Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies
Yuqiao Tan, Minzheng Wang, Shizhu He +6
Existing reinforcement learning (RL) approaches treat large language models (LLMs) as a unified policy, overlooking their internal mechanisms. In this paper, we decompose the LLM-b…
The Zero-Step Thinking: An Empirical Study of Mode Selection as Harder Early Exit in Reasoning Models
Yuqiao Tan, Shizhu He, Kang Liu +1
Reasoning models have demonstrated exceptional performance in tasks such as mathematics and logical reasoning, primarily due to their ability to engage in step-by-step thinking dur…
Towards Agentic Self-Learning LLMs in Search Environment
Wangtao Sun, Xiang Cheng, Jialin Fan +5
We study whether self-learning can scale LLM-based agents without relying on human-curated datasets or predefined rule-based rewards. Through controlled experiments in a search-age…
SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning
Huanxuan Liao, Yixing Xu, Shizhu He +6
Long-context inference in large language models (LLMs) is increasingly constrained by the KV cache bottleneck: memory usage grows linearly with sequence length, while attention com…
Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning
Fangyu Lei, Jinxiang Meng, Yiming Huang +5
Table reasoning, encompassing tasks such as table question answering, fact verification, and text-to-SQL, requires precise understanding of structured tabular data, coupled with nu…
Socratic-PRMBench: Benchmarking Process Reward Models with Systematic Reasoning Patterns
Xiang Li, Haiyang Yu, Xinghua Zhang +6
Process Reward Models (PRMs) are crucial in complex reasoning and problem-solving tasks (e.g., LLM agents with long-horizon decision-making) by verifying the correctness of each in…
Amplify Adjacent Token Differences: Enhancing Long Chain-of-Thought Reasoning with Shift-FFN
Yao Xu, Mingyu Xu, Fangyu Lei +7
Recently, models such as OpenAI-o1 and DeepSeek-R1 have demonstrated remarkable performance on complex reasoning tasks through Long Chain-of-Thought (Long-CoT) reasoning. Although…
Beyond Hard and Soft: Hybrid Context Compression for Balancing Local and Global Information Retention
Huanxuan Liao, Wen Hu, Yao Xu +3
Large Language Models (LLMs) encounter significant challenges in long-sequence inference due to computational inefficiency and redundant processing, driving interest in context com…
Neural Incompatibility: The Unbridgeable Gap of Cross-Scale Parametric Knowledge Transfer in Large Language Models
Yuqiao Tan, Shizhu He, Kang Liu +1
Large Language Models (LLMs) offer a transparent brain with accessible parameters that encode extensive knowledge, which can be analyzed, located and transferred. Consequently, a k…
Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement
Yuqiao Tan, Shizhu He, Huanxuan Liao +2
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by retrieving relevant documents from external sources and incorporating them into the context. While it…
Probabilistic Uncertain Reward Model
Wangtao Sun, Xiang Cheng, Xing Yu +5
Reinforcement learning from human feedback (RLHF) is a critical technique for training large language models. However, conventional reward models based on the Bradley-Terry model (…
GATE: Graph-based Adaptive Tool Evolution Across Diverse Tasks
Jianwen Luo, Yiming Huang, Jinxiang Meng +7
Large Language Models (LLMs) have shown great promise in tool-making, yet existing frameworks often struggle to efficiently construct reliable toolsets and are limited to single-ta…
DATA: Decomposed Attention-based Task Adaptation for Rehearsal-Free Continual Learning
Huanxuan Liao, Shizhu He, Yupu Hao +2
Continual learning (CL) is essential for Large Language Models (LLMs) to adapt to evolving real-world demands, yet they are susceptible to catastrophic forgetting (CF). While tradi…
Does RAG Really Perform Bad For Long-Context Processing?
Kun Luo, Zheng Liu, Peitian Zhang +3
The efficient processing of long context poses a serious challenge for large language models (LLMs). Recently, retrieval-augmented generation (RAG) has emerged as a promising strat…
Shuttle Between the Instructions and the Parameters of Large Language Models
Wangtao Sun, Haotian Xu, Huanxuan Liao +5
The interaction with Large Language Models (LLMs) through instructions has been extensively investigated in the research community. While instructions have been widely used as the…