5 citations · 17 across the 26 of their papers we have counts for
11 papers · 1 filter
SLPO: Scaling Latent Reasoning via a Surrogate Policy
Runyang You, Zhiyuan Liu, Yongqi Li +1
Reinforcement learning with verifiable rewards has become the predominant recipe for eliciting test-time scaling in explicit Chain-of-Thought reasoners. Yet this scaling path remai…
PalmClaw: A Native On-Device Agent Framework for Mobile Phones
Hongru Cai, Yongqi Li, Ran Wei +1
Large Language Model (LLM) agents have moved beyond generating responses to executing multi-step tasks by calling tools, observing the results, and iteratively deciding the next ac…
ToolSpec: Accelerating Tool Calling via Schema-Aware and Retrieval-Augmented Speculative Decoding
Heming Xia, Yongqi Li, Cunxiao Du +2
Tool calling has greatly expanded the practical utility of large language models (LLMs) by enabling them to interact with external applications. As LLM capabilities advance, effect…
One Adapts to Any: Meta Reward Modeling for Personalized LLM Alignment
Hongru Cai, Yongqi Li, Tiezheng Yu +4
Alignment of Large Language Models (LLMs) aims to align outputs with human preferences, and personalized alignment further adapts models to individual users. This relies on persona…
Parallel Test-Time Scaling for Latent Reasoning Models
Runyang You, Yongqi Li, Meng Liu +3
Parallel test-time scaling (TTS) is a pivotal approach for enhancing large language models (LLMs), typically by sampling multiple token-based chains-of-thought in parallel and aggr…
TokenSkip: Controllable Chain-of-Thought Compression in LLMs
Heming Xia, Chak Tou Leong, Wenjie Wang +2
Chain-of-Thought (CoT) has been proven effective in enhancing the reasoning capabilities of large language models (LLMs). Recent advancements, such as OpenAI's o1 and DeepSeek-R1,…
Large Language Models Empowered Personalized Web Agents
Hongru Cai, Yongqi Li, Wenjie Wang +4
Web agents have emerged as a promising direction to automate Web task completion based on user instructions, significantly enhancing user experience. Recently, Web agents have evol…
SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
Heming Xia, Yongqi Li, Jun Zhang +2
Speculative decoding (SD) has emerged as a widely used paradigm to accelerate LLM inference without compromising quality. It works by first employing a compact model to draft multi…
Distillation Enhanced Generative Retrieval
Yongqi Li, Zhen Zhang, Wenjie Wang +3
Generative retrieval is a promising new paradigm in text retrieval that generates identifier strings of relevant passages as the retrieval target. This paradigm leverages powerful…
GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding
Cunxiao Du, Jing Jiang, Xu Yuanchen +8
Speculative decoding is a relatively new decoding framework that leverages small and efficient draft models to reduce the latency of LLMs. In this study, we introduce GliDe and CaP…
Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding
Heming Xia, Zhe Yang, Qingxiu Dong +6
To mitigate the high inference latency stemming from autoregressive decoding in Large Language Models (LLMs), Speculative Decoding has emerged as a novel decoding paradigm for LLM…