PaperHub

Xuming Hu

~Xuming_Hu1

22
论文总数
11.0
年均投稿
5.6
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

4.8
4

Unlocking Speech Instruction Data Potential with Query Rewriting

ICLR 2025Rejected
5.0
4

LAIA-SQL: Enhancing Natural Language to SQL Generation in Multi-Table QA via Task Decomposition and Keyword Extraction

ICLR 2025withdrawn
5.5
4

Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality

ICLR 2025Poster
4.8
5

MINER: Mining the Underlying Pattern of Modality-Specific Neurons in Multimodal Large Language Models

ICLR 2025Rejected
5.3
4

ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference

ICLR 2025Rejected
4.6
5

MAD: Multi-Alignment MEG-to-Text Decoding

ICLR 2025withdrawn
4.2
5

DRUPI: Dataset Reduction Using Privileged Information

ICLR 2025withdrawn
6.4
4

LoTA-QAF: Lossless Ternary Adaptation for Quantization-Aware Fine-Tuning

NeurIPS 2025Poster
6.4
4

ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference

NeurIPS 2025Poster
6.0
3

Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers

ICLR 2025Poster
4.6
5

Interpretable Contrastive Monte Carlo Tree Search Reasoning

ICLR 2025withdrawn
5.3
4

EXPLORING RESPONSE UNCERTAINTY IN MLLMS: AN EMPIRICAL EVALUATION UNDER MISLEADING SCENARIOS

ICLR 2025Rejected
5.5
3

RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning

ICML 2025Poster
7.3
4

Don't Just Chase “Highlighted Tokens” in MLLMs: Revisiting Visual Holistic Context Retention

NeurIPS 2025Poster
4.8
4

Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models

ICLR 2025Rejected
6.6
4

OneForecast: A Universal Framework for Global and Regional Weather Forecasting

ICML 2025Poster
7.5
4

Can Watermarked LLMs be Identified by Users via Crafted Prompts?

ICLR 2025Spotlight
6.1
4

Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models

ICML 2025Poster
5.8
4

ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection

ICLR 2025Rejected