影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
41.57/100
前 13.3%
全站排名 #8,578
发表论文15 篇
平均评分
年均产出5.0 篇/年
Songyang Zhang
研究方向
Agent · Alignment · Self-supervised Learning · Large Language Models · Representation Learning
19
Rectifying LLM Thought from Lens of Optimization
ICLR 2026Poster
三作14
CompassJudger-2: A Holistic Approach Towards Generalist Judge Model
ICLR 2026Rejected
6
Coding Triangle: How Does Large Language Model Understand Code?
ICLR 2026Rejected
12
Reasoning as Meta-Learning: An Optimization Perspective to Decipher Long CoT Reasoning in LLMs
ICLR 2026Rejected
6
Knowledge-to-Verification: Unlocking Reinforcement Learning with Verifiable Rewards for LLMs in Knowledge-Intensive Domains
ICLR 2026Withdrawn
16
UnifiedVerifier: Unifying Paradigms in Automated LLM Evaluation
ICLR 2026Desk Rejected
20
How Brittle is Agent Safety? Rethinking Agent Risk under Intent Concealment and Task Complexity
ICLR 2026Withdrawn
28
Rethinking Verification for LLM Code Generation: From Generation to Testing
NeurIPS 2025Poster
16
Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning
COLM 2025Poster
34
LLaMA Decoder As Vision Transformer
ICLR 2025Rejected
20
HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models
ICLR 2025Withdrawn