Xuming Hu
~Xuming_Hu1
22
论文总数
11.0
年均投稿
平均评分
接收情况12/22
会议分布
ICLR
16
NeurIPS
3
ICML
3
发表论文 (22 篇)
202519 篇
4
Unlocking Speech Instruction Data Potential with Query Rewriting
ICLR 2025Rejected
4
LAIA-SQL: Enhancing Natural Language to SQL Generation in Multi-Table QA via Task Decomposition and Keyword Extraction
ICLR 2025withdrawn
4
Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality
ICLR 2025Poster
5
MINER: Mining the Underlying Pattern of Modality-Specific Neurons in Multimodal Large Language Models
ICLR 2025Rejected
4
ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
ICLR 2025Rejected
5
MAD: Multi-Alignment MEG-to-Text Decoding
ICLR 2025withdrawn
5
DRUPI: Dataset Reduction Using Privileged Information
ICLR 2025withdrawn
4
LoTA-QAF: Lossless Ternary Adaptation for Quantization-Aware Fine-Tuning
NeurIPS 2025Poster
4
ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
NeurIPS 2025Poster
3
Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers
ICLR 2025Poster
5
Interpretable Contrastive Monte Carlo Tree Search Reasoning
ICLR 2025withdrawn
4
EXPLORING RESPONSE UNCERTAINTY IN MLLMS: AN EMPIRICAL EVALUATION UNDER MISLEADING SCENARIOS
ICLR 2025Rejected
3
RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning
ICML 2025Poster
4
Don't Just Chase “Highlighted Tokens” in MLLMs: Revisiting Visual Holistic Context Retention
NeurIPS 2025Poster
4
Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models
ICLR 2025Rejected
4
OneForecast: A Universal Framework for Global and Regional Weather Forecasting
ICML 2025Poster
4
Can Watermarked LLMs be Identified by Users via Crafted Prompts?
ICLR 2025Spotlight
4
Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models
ICML 2025Poster
4
ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection
ICLR 2025Rejected