0

Xia Hu

Papers
23

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
23papers

Authored papers

23

A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook

arXiv 2026

2026

AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security

arXiv 2026

2026

OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs

arXiv 2026

2026

RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback

arXiv 2026

2026

DeepSight: An All-in-One LM Safety Toolkit

arXiv 2026

2026

A Trajectory-Based Safety Audit of Clawdbot (OpenClaw)

arXiv 2026

2026

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

arXiv 2026

2026

Decoupled Reasoning with Implicit Fact Tokens (DRIFT): A Dual-Model Framework for Efficient Long-Context Inference

arXiv 2026

2026

Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

arXiv 2025

2025

70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float

arXiv 2025

2025

Give Me FP32 or Give Me Death? Challenges and Solutions for Reproducible Reasoning

arXiv 2025

2025

More for Keys, Less for Values: Adaptive KV Cache Quantization

arXiv 2025

2025

KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

arXiv 2024

2024

KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches

arXiv 2024

2024

LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

arXiv 2024

2024

Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond

arXiv 2023

2023

FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods

arXiv 2023

2023

Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model

winner-take-all-column-row-sampling-for

2023

Data-centric Artificial Intelligence: A Survey

arXiv 2023

2023

DIVISION: Memory Efficient Training via Dual Activation Precision

arXiv 2022

2022

Mitigating Gender Bias in Captioning Systems

arXiv 2020

2020

RLCard: A Toolkit for Reinforcement Learning in Card Games

arXiv 2019

2019

Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks

arXiv 2019

2019

Affiliations

No known affiliations.

Frequent co-authors

10

from 23 papers