Haohan Wang

Optimal Aggregation of LLM and PRM Signals for Efficient Test-Time Scaling

SIPDO: Closed-Loop Prompt Optimization via Synthetic Data Feedback

Controlling Output Rankings in Generative Engines for LLM-based Search

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Resource-Constrained Decision Making and Revision

Pick Your Textual Gradients

From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation Models

PREMISE: Scalable and Strategic Prompt Optimization for Efficient Mathematical Reasoning in Large Models

Spectral-Aware Sparse Communication and Entropy-Balanced Tasking in Multi-Agent Systems

Modeling Normalcy: A Zero-Negative-Shot Defense Against Prompt Injection

Revolve: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization

Examining Alignment of Large Language Models through Representative Heuristics: the case of political stereotypes

Evaluating the Inductive Abilities of Large Language Models: Why Chain-of-Thought Reasoning Sometimes Hurts More Than Helps

CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation

Conflict-Aware Adversarial Training

GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs

GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing

GenoAgent: A Baseline method for LLM-Based Exploration of Gene Expression Data in Alignment with Bioinformaticians

HessianGrad: Optimizing AI Systems with Hessian-Aware Textual Gradients

ADAPT: Alzheimer's Diagnosis through Adaptive Profiling Transformers

AutoModel: Autonomous Model Development for Image Classification with LLM Agents

Beyond Finite Data: Towards Data-free Out-of-distribution Generalization via Extrapolation