activity
20222026
most citedCUTS: Neural Causal Discovery from Irregular Time-Series Data

9 citations · 14 across the 12 of their papers we have counts for

collaborators
Showing cs.AIShow all

2 papers · 1 filter

cs.AI2026

Anchoring What Matters: A Dual-Level Learning Framework for Visually-Grounded Multimodal Reasoning

Xinxin Song, Siyuan Li, Tingxiong Xiao +1

Reinforcement learning with verifiable rewards (RLVR) has significantly improved the reasoning capabilities of large vision-language models (LVLMs). However, standard on-policy RLV…

cs.AI2026

CARE: Contrastive Anchor-based Rubric Evolution for Large Language Model Post-Training

Siyuan Li, Xinxin Song, Chen Ruinian +5

Rubric-based reinforcement learning decomposes open-ended instructions into prompt-specific, flexible rubrics, making it better suited than reinforcement learning with verifiable r…