activity
20202026
most citedText2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction

14 citations · 93 across the 74 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2026

ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation

Qingyu Zhang, Qianhao Yuan, Hongyu Lin +5

Structured pruning is a hardware-friendly way to compress LLMs, but it is mostly validated on multiple-choice recognition tasks, while the same compressed checkpoints can collapse…

cs.LG2026

OmniFocus: Query-Guided Modality-Balanced Token Compression for Omni-Modal Large Language Models

Shijie Cao, Qingyu Zhang, Boxi Yu +6

Omni modal large language models (OmniLLMs) have attracted wide attention for their ability to jointly process audio and video, but they generate large token sequences under audio-…

cs.LG2026

Tackling Length Inflation Without Trade-offs: Group Relative Reward Rescaling for Reinforcement Learning

Zichao Li, Jie Lou, Fangchen Dong +8

Reinforcement learning significantly enhances LLM capabilities but suffers from a critical issue: length inflation, where models adopt verbosity or inefficient reasoning to maximiz…

cs.LG2026

P^2O: Joint Policy and Prompt Optimization

Xinyu Lu, Kaiqi Zhang, Jinglin Yang +6

Reinforcement Learning with Verifiable Rewards (RLVR) enhances Large Language Model (LLM) reasoning but suffers from advantage collapse on ``hard samples'' where all rollouts fail.…

cs.LG2026

Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards

Zhengzhao Ma, Xueru Wen, Boxi Cao +6

Reinforcement Learning from Verifiable Rewards (RLVR) significantly enhances large language models (LLMs) reasoning but severely suffers from calibration degeneration, where models…

cs.LG2024

A Unified View of Delta Parameter Editing in Post-Trained Large-Scale Models

Qiaoyu Tang, Le Yu, Bowen Yu +5

Post-training has emerged as a crucial paradigm for adapting large-scale pre-trained models to various tasks, whose effects are fully reflected by delta parameters (i.e., the dispa…