Picture for Zhihao Zhang

Zhihao Zhang

PFDial: A Structured Dialogue Instruction Fine-tuning Method Based on UML Flowcharts

Add code
Mar 09, 2025
Viaarxiv icon

Real-time Spatial-temporal Traversability Assessment via Feature-based Sparse Gaussian Process

Add code
Mar 06, 2025
Viaarxiv icon

SEB-Naver: A SE(2)-based Local Navigation Framework for Car-like Robots on Uneven Terrain

Add code
Mar 05, 2025
Viaarxiv icon

EliteKV: Scalable KV Cache Compression via RoPE Frequency Selection and Joint Low-Rank Projection

Add code
Mar 03, 2025
Viaarxiv icon

Extensive Exploration in Complex Traffic Scenarios using Hierarchical Reinforcement Learning

Add code
Jan 25, 2025
Viaarxiv icon

AdaServe: SLO-Customized LLM Serving with Fine-Grained Speculative Decoding

Add code
Jan 21, 2025
Viaarxiv icon

Communication Bounds for the Distributed Experts Problem

Add code
Jan 06, 2025
Viaarxiv icon

LLMs can realize combinatorial creativity: generating creative ideas via LLMs for scientific research

Add code
Dec 18, 2024
Figure 1 for LLMs can realize combinatorial creativity: generating creative ideas via LLMs for scientific research
Figure 2 for LLMs can realize combinatorial creativity: generating creative ideas via LLMs for scientific research
Figure 3 for LLMs can realize combinatorial creativity: generating creative ideas via LLMs for scientific research
Figure 4 for LLMs can realize combinatorial creativity: generating creative ideas via LLMs for scientific research
Viaarxiv icon

A Claim Decomposition Benchmark for Long-form Answer Verification

Add code
Oct 16, 2024
Figure 1 for A Claim Decomposition Benchmark for Long-form Answer Verification
Figure 2 for A Claim Decomposition Benchmark for Long-form Answer Verification
Figure 3 for A Claim Decomposition Benchmark for Long-form Answer Verification
Figure 4 for A Claim Decomposition Benchmark for Long-form Answer Verification
Viaarxiv icon

TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention

Add code
Oct 07, 2024
Viaarxiv icon