5 citations · 6 across the 15 of their papers we have counts for
9 papers · 1 filter
ARBOR: Online Process Rewards via a Reusable Rubric Buffer for Search Agents
Zheng Liu, Longxiang Zhang, Xintong Wang +8
LLM-based search agents are trained predominantly with outcome-only reward, leaving the search process itself unsupervised. This signal degenerates on outcome-homogeneous groups wh…
Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning
Yanyu Zhu, Hoilam Pao, Niu Hu +6
Large Language Models suffer from slow autoregressive inference. While self-speculative decoding accelerates this process, its efficiency is hampered by static configurations like…
JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency
Aichen Cai, Anmeng Zhang, Anyu Li +66
We introduce JoyAI-LLM Flash, an efficient Mixture-of-Experts (MoE) language model designed to redefine the trade-off between strong performance and token efficiency in the sub-50B…
SemantiCache: Efficient KV Cache Compression via Semantic Chunking and Clustered Merging
Shunlong Wu, Hai Lin, Shaoshen Chen +5
Existing KV cache compression methods generally operate on discrete tokens or non-semantic chunks. However, such approaches often lead to semantic fragmentation, where linguistical…
R-Align: Enhancing Generative Reward Models through Rationale-Centric Meta-Judging
Yanlin Lai, Mitt Huang, Hangyu Guo +11
Reinforcement Learning from Human Feedback (RLHF) remains indispensable for aligning large language models (LLMs) in subjective domains. To enhance robustness, recent work shifts t…
Auxiliary-Hyperparameter-Free Sampling: Entropy Equilibrium for Text Generation
Xiaodong Cai, Hai Lin, Shaoxiong Zhan +5
Token sampling strategies critically influence text generation quality in large language models (LLMs). However, existing methods introduce additional hyperparameters, requiring ex…
MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging Synthetic Problems with a Reinforced Policy
Shaoxiong Zhan, Yanlin Lai, Ziyu Lu +3
Large language models have achieved substantial progress in mathematical reasoning, yet their advancement is limited by the scarcity of high-quality, high-difficulty training data.…
A Hierarchical Framework for Measuring Scientific Paper Innovation via Large Language Models
Hongming Tan, Shaoxiong Zhan, Fengwei Jia +2
Measuring scientific paper innovation is both important and challenging. Existing content-based methods often overlook the full-paper context, fail to capture the full scope of inn…
QAEA-DR: A Unified Text Augmentation Framework for Dense Retrieval
Hongming Tan, Shaoxiong Zhan, Hai Lin +2
In dense retrieval, embedding long texts into dense vectors can result in information loss, leading to inaccurate query-text matching. Additionally, low-quality texts with excessiv…