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
52.21/100
前 7.5%
全站排名 #4,810
发表论文19 篇
平均评分
年均产出9.5 篇/年
Zhuokai Zhao
研究方向
Active learning · Trustworthy LLMs · Multimodal LLMs · Recommender system · Explainable ML · Visualization
31
Scaling Agent Learning via Experience Synthesis
ICLR 2026Poster
二作9
Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment
ICLR 2026Rejected
二作11
StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding
ICLR 2026Rejected
二作19
Exploring System-1 and System-2 Communication for Latent Reasoning in LLMs
ICLR 2026Rejected
二作6
Multi-Sample Preference Optimization for Generative Model Alignment
ICLR 2026Rejected
二作16
Transfer between Modalities with MetaQueries
ICLR 2026Rejected
21
LILO: Bayesian Optimization with Interactive Natural Language Feedback
ICLR 2026Rejected
13
Let it Calm: Exploratory Annealed Decoding for Verifiable Reinforcement Learning
ICLR 2026Rejected
通讯7
DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts
ICLR 2026Rejected
5
CircuitProbe: Dissecting Spatiotemporal Visual Semantics with Circuit Tracing
ICLR 2026Withdrawn
三作25
Thought Communication in Multiagent Collaboration
NeurIPS 2025Spotlight
二作22
S'MoRE: Structural Mixture of Residual Experts for Parameter-Efficient LLM Fine-tuning
NeurIPS 2025Poster
三作26
Quantifying Generalization Complexity for Large Language Models
ICLR 2025Poster
50
MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?
ICLR 2025Rejected
22
Enhancing Vision-Language Model Reliability with Uncertainty-Guided Dropout Decoding
NeurIPS 2025Poster
23
Boosting LLM Reasoning via Spontaneous Self-Correction
COLM 2025Poster
19
Preference Optimization with Multi-Sample Comparisons
ICLR 2025Rejected
二作16
RANKCLIP: Ranking-Consistent Language-Image Pretraining
ICLR 2025Rejected
二作4
Direct Acquisition Optimization for Low-Budget Active Learning
ICLR 2025Withdrawn
一作