William Yang Wang
~William_Yang_Wang2
39
论文总数
19.5
年均投稿
平均评分
接收情况21/39
会议分布
ICLR
27
COLM
6
NeurIPS
4
ICML
2
发表论文 (39 篇)
202523 篇
3
DebUnc: Improving Large Language Model Agent Communication Via Uncertainty Metrics
ICLR 2025withdrawn
4
ThoughtTerminator: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models
COLM 2025Poster
5
Gödel Agent: A Self-Referential Framework Helps for Recursively Self-Improvement
ICLR 2025Rejected
4
MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents
ICML 2025Poster
4
VSP: Assessing the dual challenges of perception and reasoning in spatial planning tasks for MLLMs
ICLR 2025withdrawn
4
Pixelated Instructions: Can Multimodal Large Language Models Follow Printed Instructions in Images?
ICLR 2025Rejected
5
Understanding the Interplay between Parametric and Contextual Knowledge for Large Language Models
ICLR 2025Rejected
3
Compact Multimodal Context Represenations Using Visual Tokens
ICLR 2025Rejected
4
TC-Bench: Benchmarking Temporal Compositionality in Conditional Video Generation
ICLR 2025Rejected
4
SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement
ICLR 2025Poster
4
Detecting Training Data of Large Language Models via Expectation Maximization
ICLR 2025Rejected
3
Discovering Factor Level Preferences to Improve Human-Model Alignment
ICLR 2025Rejected
5
Weak-to-Strong Jailbreaking on Large Language Models
ICLR 2025Rejected
4
Generalization v.s. Memorization: Tracing Language Models’ Capabilities Back to Pretraining Data
ICLR 2025Poster
3
Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling
ICLR 2025Poster
5
T2V-Turbo-v2: Enhancing Video Model Post-Training through Data, Reward, and Conditional Guidance Design
ICLR 2025Poster
3
Weak-to-Strong Jailbreaking on Large Language Models
ICML 2025Poster
4
COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement
ICLR 2025Rejected
4
MuSLR: Multimodal Symbolic Logical Reasoning
NeurIPS 2025Poster
5
MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos
ICLR 2025Poster
5
Can Editing LLMs Inject Harm?
ICLR 2025Rejected
4
MMSci: A Dataset for Graduate-Level Multi-Discipline Multimodal Scientific Understanding
ICLR 2025Rejected
3
MLGym: A New Framework and Benchmark for Advancing AI Research Agents
COLM 2025Poster
202416 篇
4
Benchmarks as Microscopes: A Call for Model Metrology
COLM 2024Poster
4
ToolDec: Syntax Error-Free and Generalizable Tool Use for LLMs via Finite-State Decoding
ICLR 2024Rejected
4
FASTopic: Pretrained Transformer is a Fast, Adaptive, Stable, and Transferable Topic Model
NeurIPS 2024Poster
4
Neuroformer: Multimodal and Multitask Generative Pretraining for Brain Data
ICLR 2024Poster
4
Guiding Instruction-based Image Editing via Multimodal Large Language Models
ICLR 2024Spotlight
4
Language Control Diffusion: Efficiently Scaling through Space, Time, and Tasks
ICLR 2024Poster
4
Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense?
COLM 2024Poster
4
Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models
ICLR 2024withdrawn
3
DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text
ICLR 2024Poster
4
Guiding Language Model Reasoning with Planning Tokens
COLM 2024Poster
4
Who Evaluates the Evaluations? Objectively Scoring Text-to-Image Prompt Coherence Metrics with T2IScoreScore (TS2)
NeurIPS 2024Spotlight
3
Multimodal Procedural Planning via Dual Text-Image Prompting
ICLR 2024withdrawn
5
T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback
NeurIPS 2024Poster
3
Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models
COLM 2024Poster
4
Mastering Robot Manipulation with Multimodal Prompts through Pretraining and Multi-task Fine-tuning
ICLR 2024Rejected
4
Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings
ICLR 2024withdrawn