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
77.41/100
前 1.6%
全站排名 #1,054
发表论文19 篇
平均评分
年均产出6.3 篇/年
Suhang Wang
研究方向
Graph Neural Networks · Generative Adversarial Networks · Adversarial Learning · Graph Mining · Deep Learning
20
Agent-REINFORCE: Searching Compute-Optimal Multi-LLM Collaboration Graph for Test-Time Scaling
ICLR 2026Rejected
通讯29
Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberation
ICLR 2026Poster
通讯27
How Far Are LLMs from Professional Poker Players? Revisiting Game-Theoretic Reasoning with Agentic Tool Use
ICLR 2026Poster
通讯14
TRAJECT-Bench:A Trajectory-Aware Benchmark for Evaluating Agentic Tool Use
ICLR 2026Poster
31
Seeing but Not Believing: Probing the Disconnect Between Visual Attention and Answer Correctness in VLMs
ICLR 2026Poster
30
Bradley-Terry and Multi-Objective Reward Modeling Are Complementary
ICLR 2026Poster
通讯20
Adaptive Test-Time Reasoning via Reward-Guided Dual-Phase Search
ICLR 2026Withdrawn
21
Robustness Inspired Graph Backdoor Defense
ICLR 2025Oral
通讯24
Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy
NeurIPS 2025Poster
24
DualEqui: A Dual-Space Hierarchical Equivariant Network for Large Biomolecules
NeurIPS 2025Poster
通讯22
AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks
NeurIPS 2025Poster
通讯29
Catastrophic Failure of LLM Unlearning via Quantization
ICLR 2025Poster
通讯34
Divide-Verify-Refine: Aligning LLM Responses with Complex Instructions
ICLR 2025Rejected
通讯6
Robust Watermarking for Diffusion Models: A Unified Multi-Dimensional Recipe
ICLR 2025Withdrawn