Picture for Boxing Chen

Boxing Chen

Huawei Noah's Ark Lab

Balcony: A Lightweight Approach to Dynamic Inference of Generative Language Models

Add code
Mar 06, 2025
Viaarxiv icon

R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning

Add code
Feb 27, 2025
Viaarxiv icon

ReGLA: Refining Gated Linear Attention

Add code
Feb 03, 2025
Viaarxiv icon

ZETA: Leveraging Z-order Curves for Efficient Top-k Attention

Add code
Jan 24, 2025
Viaarxiv icon

Rethinking Post-Training Quantization: Introducing a Statistical Pre-Calibration Approach

Add code
Jan 15, 2025
Figure 1 for Rethinking Post-Training Quantization: Introducing a Statistical Pre-Calibration Approach
Figure 2 for Rethinking Post-Training Quantization: Introducing a Statistical Pre-Calibration Approach
Figure 3 for Rethinking Post-Training Quantization: Introducing a Statistical Pre-Calibration Approach
Figure 4 for Rethinking Post-Training Quantization: Introducing a Statistical Pre-Calibration Approach
Viaarxiv icon

Batch-Max: Higher LLM Throughput using Larger Batch Sizes and KV Cache Compression

Add code
Dec 07, 2024
Viaarxiv icon

Adapting Large Language Models to Log Analysis with Interpretable Domain Knowledge

Add code
Dec 02, 2024
Viaarxiv icon

Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination

Add code
Oct 22, 2024
Figure 1 for Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination
Figure 2 for Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination
Figure 3 for Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination
Figure 4 for Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination
Viaarxiv icon

LogLM: From Task-based to Instruction-based Automated Log Analysis

Add code
Oct 12, 2024
Figure 1 for LogLM: From Task-based to Instruction-based Automated Log Analysis
Figure 2 for LogLM: From Task-based to Instruction-based Automated Log Analysis
Figure 3 for LogLM: From Task-based to Instruction-based Automated Log Analysis
Figure 4 for LogLM: From Task-based to Instruction-based Automated Log Analysis
Viaarxiv icon

Draft on the Fly: Adaptive Self-Speculative Decoding using Cosine Similarity

Add code
Oct 01, 2024
Viaarxiv icon