activity
20242026
most citedConcrete Subspace Learning based Interference Elimination for Multi-task Model Fusion

1 citations · 2 across the 22 of their papers we have counts for

collaborators
Showing cs.CLShow all

29 papers · 1 filter

cs.CL2026

Diagnosing and Mitigating Thinking Collapse in On-Policy Self-Distillation

Keqin Peng, Chen Li, Yuanxin Ouyang +2

On-Policy Self-Distillation (OPSD) has emerged as a crucial paradigm for enhancing and aligning Large Language Models (LLMs). However, in complex reasoning tasks, OPSD paradoxicall…

cs.CL2026

Beyond Scalar Scores: Exploring LLM-based Metrics for Clinical Significance Evaluation in Radiology Reports

Qingyu Lu, Ruochen Li, Liang Ding +3

Reliable evaluation of generated radiology reports requires strict clinical accuracy, as omitted critical findings or mischaracterized radiographic observations can directly affect…

cs.CL2026

ARBOR: Online Process Rewards via a Reusable Rubric Buffer for Search Agents

Zheng Liu, Longxiang Zhang, Xintong Wang +8

LLM-based search agents are trained predominantly with outcome-only reward, leaving the search process itself unsupervised. This signal degenerates on outcome-homogeneous groups wh…

cs.CL2026

VIDA: A dataset for Visually Dependent Ambiguity in Multimodal Machine Translation

Jingheng Pan, Xintong Wang, Longyue Wang +3

Ambiguity resolution is a key challenge in multimodal machine translation (MMT), where models must genuinely leverage visual input to map an ambiguous expression to its intended me…

cs.CL2026

Better, Faster: Harnessing Self-Improvement in Large Reasoning Models

Qihuang Zhong, Liang Ding, Juhua Liu +3

Self-improvement training enables the large reasoning models (LRMs) to improve themselves by self-generating reasoning trajectories as training data without external supervision. H…

cs.CL2026

The Bitter Lesson of Diffusion Language Models for Agentic Workflows: A Comprehensive Reality Check

Qingyu Lu, Liang Ding, Kanjian Zhang +2

The pursuit of real-time agentic interaction has driven interest in Diffusion-based Large Language Models (dLLMs) as alternatives to auto-regressive backbones, promising to break t…