Picture for Haohan Wang

Haohan Wang

Socratic Chart: Cooperating Multiple Agents for Robust SVG Chart Understanding

Add code
Apr 14, 2025
Viaarxiv icon

Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems

Add code
Mar 31, 2025
Viaarxiv icon

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

Add code
Mar 30, 2025
Viaarxiv icon

IMPROVE: Iterative Model Pipeline Refinement and Optimization Leveraging LLM Agents

Add code
Feb 25, 2025
Viaarxiv icon

Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypes

Add code
Jan 27, 2025
Figure 1 for Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypes
Figure 2 for Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypes
Figure 3 for Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypes
Figure 4 for Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypes
Viaarxiv icon

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

Add code
Dec 04, 2024
Viaarxiv icon

Conflict-Aware Adversarial Training

Add code
Oct 21, 2024
Viaarxiv icon

DistDD: Distributed Data Distillation Aggregation through Gradient Matching

Add code
Oct 11, 2024
Viaarxiv icon

Simple Unsupervised Knowledge Distillation With Space Similarity

Add code
Sep 20, 2024
Viaarxiv icon

DS-ViT: Dual-Stream Vision Transformer for Cross-Task Distillation in Alzheimer's Early Diagnosis

Add code
Sep 11, 2024
Figure 1 for DS-ViT: Dual-Stream Vision Transformer for Cross-Task Distillation in Alzheimer's Early Diagnosis
Figure 2 for DS-ViT: Dual-Stream Vision Transformer for Cross-Task Distillation in Alzheimer's Early Diagnosis
Figure 3 for DS-ViT: Dual-Stream Vision Transformer for Cross-Task Distillation in Alzheimer's Early Diagnosis
Figure 4 for DS-ViT: Dual-Stream Vision Transformer for Cross-Task Distillation in Alzheimer's Early Diagnosis
Viaarxiv icon