1 citations · 1 across the 10 of their papers we have counts for
11 papers
AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters
Yu-Yang Qian, Hao-Cong Wu, Chen Chen +4
Speculative decoding, in which a lightweight draft model first generates a draft sequence that is then verified by the target model, has become a prevalent paradigm for acceleratin…
Where Hindsight Credit Can Reside: A Signed-Capacity View of Token Updates in RLVR
Yuhang He, Haodong Wu, Siyi Liu +7
Reinforcement Learning with Verifiable Rewards (RLVR) improves the reasoning ability of Large Language Models (LLMs), but sparse outcome rewards make token-level credit assignment…
C-ReD: A Comprehensive Chinese Benchmark for AI-Generated Text Detection Derived from Real-World Prompts
Chenxi Qing, Junxi Wu, Zheng Liu +5
Recently, large language models (LLMs) are capable of generating highly fluent textual content. While they offer significant convenience to humans, they also introduce various risk…
Alignment Imprint: Zero-Shot AI-Generated Text Detection via Provable Preference Discrepancy
Junxi Wu, Kailin Huang, Dongjian Hu +4
Detecting AI-generated text is an important but challenging problem. Existing likelihood-based detection methods are often sensitive to content complexity and may exhibit unstable…
The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems
Yihao Zhang, Kai Wang, Jiangrong Wu +7
Large Language Models (LLMs) face prominent security risks from jailbreaking, a practice that manipulates models to bypass built-in security constraints and generate unethical or u…
LoopGuard: Breaking Self-Reinforcing Attention Loops via Dynamic KV Cache Intervention
Dongjie Xu, Hao Wu, Weijie Shi +7
Through systematic experiments on long-context generation, we observe a damaging failure mode in which decoding can collapse into persistent repetition loops. We find that this deg…
Internal Knowledge Without External Expression: Probing the Generalization Boundary of a Classical Chinese Language Model
Jiuting Chen, Yuan Lian, Hao Wu +4
We train a 318M-parameter Transformer language model from scratch on a curated corpus of 1.56 billion tokens of pure Classical Chinese, with zero English characters or Arabic numer…
UniToolCall: Unifying Tool-Use Representation, Data, and Evaluation for LLM Agents
Yijuan Liang, Xinghao Chen, Yifan Ge +5
Tool-use capability is a fundamental component of LLM agents, enabling them to interact with external systems through structured function calls. However, existing research exhibits…
When Drafts Evolve: Speculative Decoding Meets Online Learning
Yu-Yang Qian, Hao-Cong Wu, Yichao Fu +2
Speculative decoding has emerged as a widely adopted paradigm for accelerating large language model inference, where a lightweight draft model rapidly generates candidate tokens th…
vLLM Semantic Router: Signal Driven Decision Routing for Mixture-of-Modality Models
Xunzhuo Liu, Huamin Chen, Samzong Lu +30
As large language models (LLMs) diversify across modalities, capabilities, and cost profiles, the problem of intelligent request routing: selecting the right model for each query a…
AdaSpec: Adaptive Speculative Decoding for Fast, SLO-Aware Large Language Model Serving
Kaiyu Huang, Hao Wu, Zhubo Shi +3
Cloud-based Large Language Model (LLM) services often face challenges in achieving low inference latency and meeting Service Level Objectives (SLOs) under dynamic request patterns.…