1 citations · 1 across the 12 of their papers we have counts for
14 papers
QAM: Quadratic-Accurate Checkpoint Merging via Sequential Consistency
Shihao Wang, Rui Kong, Xinran Chen +7
Saved checkpoints record states along a training trajectory, but generally do not determine the updates at states that would be visited under a different schedule. We study how acc…
SWRouter: Similarity-Contractive Window Routing for Multi-Turn Large Language Model Conversations
Yu Wang, Yuchen Li, Rui Kong +11
Large language models exhibit complementary strengths, motivating routing methods that dispatch each query to the most suitable model. Although existing routers are effective in si…
TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning
Changle Qu, Sunhao Dai, Hengyi Cai +4
Tool-Integrated Reasoning (TIR) enables LLMs to solve complex tasks through iterative tool interactions. However, existing reinforcement learning methods often rely on trajectory-l…
SCOPE-RL: Optimizing Reasoning Paths Before and After Success
Xiaojian Liu, Han Xu, Jianqiang Xia +6
Reinforcement learning with verifiable rewards (RLVR) optimizes LLMs using sparse verifiable final-answer rewards. This sparse anchor reliably verifies whether a trajectory succeed…
STAMP: Provenance-Guided Credit Assignment for Deep Search Agents
Ke Xu, Han Xu, Xinran Chen +6
Reinforcement learning for deep-search agents has largely focused on trajectory-level scoring -- outcome correctness, citation-aware rewards, and evidence coverage. Yet the actions…
Measuring Maximum Activations in Open Large Language Models
Luxuan Chen, Han Tian, Xinran Chen +9
The dynamic range of activations is a first-order constraint for low-bit quantization, activation scaling, and stable LLM inference. Prior work characterized outlier features and m…
EndPrompt: Efficient Long-Context Extension via Terminal Anchoring
Han Tian, Luxuan Chen, Xinran Chen +10
Extending the context window of large language models typically requires training on sequences at the target length, incurring quadratic memory and computational costs that make lo…
Not All Preferences Deserve Gradients: Understanding Gradient Utility in Offline Reasoning Alignment
Hui Wu, Hengyi Cai, Jinman Zhao +6
Offline preference optimization aligns reasoning models from fixed chosen--rejected pairs, yet standard methods apply gradient updates from every pair regardless of its training va…
FlexSpec: Frozen Drafts Meet Evolving Targets in Edge-Cloud Collaborative LLM Speculative Decoding
Yuchen Li, Rui Kong, Zhonghao Lyu +11
Deploying large language models (LLMs) in mobile and edge computing environments is constrained by limited on-device resources, scarce wireless bandwidth, and frequent model evolut…
Tracking Drift: Variation-Aware Entropy Scheduling for Non-Stationary Reinforcement Learning
Tongxi Wang, Zhuoyang Xia, Xinran Chen +1
Real-world reinforcement learning often faces environment drift, but most existing methods rely on static entropy coefficients/target entropy, causing over-exploration during stabl…
Grounding Long-Context Reasoning with Contextual Normalization for Retrieval-Augmented Generation
Jiamin Chen, Yuchen Li, Xinyu Ma +5
Retrieval-Augmented Generation (RAG) has become an essential approach for extending the reasoning and knowledge capacity of large language models (LLMs). While prior research has p…
Towards AI Search Paradigm
Yuchen Li, Hengyi Cai, Rui Kong +20
In this paper, we introduce the AI Search Paradigm, a comprehensive blueprint for next-generation search systems capable of emulating human information processing and decision-maki…
Boosting Blockchain Throughput: Parallel EVM Execution with Asynchronous Storage for Reddio
Xiaodong Qi, Xinran Chen, Asiy +1
The increasing adoption of blockchain technology has led to a growing demand for higher transaction throughput. Traditional blockchain platforms, such as Ethereum, execute transact…
Improving Non-autoregressive Machine Translation with Error Exposure and Consistency Regularization
Xinran Chen, Sufeng Duan, Gongshen Liu
Being one of the IR-NAT (Iterative-refinemennt-based NAT) frameworks, the Conditional Masked Language Model (CMLM) adopts the mask-predict paradigm to re-predict the masked low-con…