Picture for Kexun Zhang

Kexun Zhang

HardTests: Synthesizing High-Quality Test Cases for LLM Coding

Add code
May 30, 2025
Viaarxiv icon

Programming by Examples Meets Historical Linguistics: A Large Language Model Based Approach to Sound Law Induction

Add code
Jan 27, 2025
Figure 1 for Programming by Examples Meets Historical Linguistics: A Large Language Model Based Approach to Sound Law Induction
Figure 2 for Programming by Examples Meets Historical Linguistics: A Large Language Model Based Approach to Sound Law Induction
Figure 3 for Programming by Examples Meets Historical Linguistics: A Large Language Model Based Approach to Sound Law Induction
Figure 4 for Programming by Examples Meets Historical Linguistics: A Large Language Model Based Approach to Sound Law Induction
Viaarxiv icon

Embracing AI in Education: Understanding the Surge in Large Language Model Use by Secondary Students

Add code
Nov 27, 2024
Viaarxiv icon

SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement

Add code
Oct 29, 2024
Figure 1 for SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement
Figure 2 for SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement
Figure 3 for SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement
Figure 4 for SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement
Viaarxiv icon

Scaling LLM Inference with Optimized Sample Compute Allocation

Add code
Oct 29, 2024
Figure 1 for Scaling LLM Inference with Optimized Sample Compute Allocation
Figure 2 for Scaling LLM Inference with Optimized Sample Compute Allocation
Figure 3 for Scaling LLM Inference with Optimized Sample Compute Allocation
Figure 4 for Scaling LLM Inference with Optimized Sample Compute Allocation
Viaarxiv icon

Revealing the Barriers of Language Agents in Planning

Add code
Oct 16, 2024
Figure 1 for Revealing the Barriers of Language Agents in Planning
Figure 2 for Revealing the Barriers of Language Agents in Planning
Figure 3 for Revealing the Barriers of Language Agents in Planning
Figure 4 for Revealing the Barriers of Language Agents in Planning
Viaarxiv icon

Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents

Add code
Aug 13, 2024
Viaarxiv icon

Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data

Add code
Jul 20, 2024
Figure 1 for Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data
Figure 2 for Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data
Figure 3 for Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data
Figure 4 for Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data
Viaarxiv icon

Can Large Language Models Code Like a Linguist?: A Case Study in Low Resource Sound Law Induction

Add code
Jun 18, 2024
Figure 1 for Can Large Language Models Code Like a Linguist?: A Case Study in Low Resource Sound Law Induction
Figure 2 for Can Large Language Models Code Like a Linguist?: A Case Study in Low Resource Sound Law Induction
Figure 3 for Can Large Language Models Code Like a Linguist?: A Case Study in Low Resource Sound Law Induction
Figure 4 for Can Large Language Models Code Like a Linguist?: A Case Study in Low Resource Sound Law Induction
Viaarxiv icon

DeFT: Flash Tree-attention with IO-Awareness for Efficient Tree-search-based LLM Inference

Add code
Mar 30, 2024
Viaarxiv icon