activity
20202026
most citedRegularizing Dialogue Generation by Imitating Implicit Scenarios

4 citations · 15 across the 35 of their papers we have counts for

collaborators
Showing 2025Show all

13 papers · 1 filter

cs.CV2025

Stitch and Tell: A Structured Multimodal Data Augmentation Method for Spatial Understanding

Hang Yin, Xiaomin He, PeiWen Yuan +5

Existing vision-language models often suffer from spatial hallucinations, i.e., generating incorrect descriptions about the relative positions of objects in an image. We argue that…

cs.LG2025

Breaking the Self-Confirming Loop: Diagnosing and Mitigating Systemic Reward Bias in Self-Rewarding RL

Chuyi Tan, Peiwen Yuan, Xinglin Wang +8

Reinforcement learning with verifiable rewards (RLVR) efficiently scales the reasoning ability of large language models (LLMs) but is bottlenecked by scarce labeled data. Reinforce…

cs.LG2025

PatternKV: Flattening KV Representation Expands Quantization Headroom

Ji Zhang, Yiwei Li, Shaoxiong Feng +8

KV cache in autoregressive LLMs eliminates redundant recomputation but has emerged as the dominant memory and bandwidth bottleneck during inference, notably with long contexts and…

cs.LG2025

Every Rollout Counts: Optimal Resource Allocation for Efficient Test-Time Scaling

Xinglin Wang, Yiwei Li, Shaoxiong Feng +7

Test-Time Scaling (TTS) improves the performance of Large Language Models (LLMs) by using additional inference-time computation to explore multiple reasoning paths through search.…

cs.AI2025

Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules

Yueqi Zhang, Peiwen Yuan, Shaoxiong Feng +7

Human-AI conversation frequently relies on quoting earlier text-"check it with the formula I just highlighted"-yet today's large language models (LLMs) lack an explicit mechanism f…

cs.CL2025

Silencer: From Discovery to Mitigation of Self-Bias in LLM-as-Benchmark-Generator

Peiwen Yuan, Yiwei Li, Shaoxiong Feng +7

LLM-as-Benchmark-Generator methods have been widely studied as a supplement to human annotators for scalable evaluation, while the potential biases within this paradigm remain unde…