Xia Hu
~Xia_Hu4
20
论文总数
10.0
年均投稿
平均评分
接收情况6/20
会议分布
ICLR
14
NeurIPS
4
ICML
2
发表论文 (20 篇)
202510 篇
4
70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)
NeurIPS 2025Poster
4
STRUCTDROP: A STRUCTURED RANDOM ALGORITHM TOWARDS EFFICIENT LARGE-SCALE GRAPH TRAINING
ICLR 2025Rejected
4
Learning to Route LLMs with Confidence Tokens
ICML 2025Poster
3
Weighted Diversified Sampling for Efficient Data-Driven Single-Cell Gene-Gene Interaction Discovery
ICLR 2025Rejected
4
Advancing Table Understanding of Large Language Models via Feature Re-ordering
ICLR 2025withdrawn
4
Confident or Seek Stronger: Exploring Uncertainty-Based Small LM Routing From Benchmarking to Generalization
NeurIPS 2025Rejected
4
Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference
NeurIPS 2025Oral
4
Graph Transformers Get the GIST: Graph Invariant Structural Trait for Refined Graph Encoding
ICML 2025Rejected
6
Attack on LLMs: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem
ICLR 2025withdrawn
4
MQuAKE-Remastered: Multi-Hop Knowledge Editing Can Only Be Advanced with Reliable Evaluations
ICLR 2025Spotlight
202410 篇
4
STRUCTDROP: A STRUCTURED RANDOM ALGORITHM TOWARDS EFFICIENT LARGE-SCALE GRAPH TRAINING
ICLR 2024Rejected
4
GrowLength: Accelerating LLMs Pretraining by Progressively Growing Training Length
ICLR 2024Rejected
3
LeanFlex-GKP: Advancing Hassle-Free Structured Pruning with Simple Flexible Group Count
ICLR 2024Rejected
4
Compress, Then Prompt: Improving Accuracy-Efficiency Trade-off of LLM Inference with Transferable Prompt
ICLR 2024Rejected
4
FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods
ICLR 2024Poster
5
UNITE:Universally Trustworthy GNN Via Subgraph Identification
ICLR 2024Rejected
3
Editable Graph Neural Network for Node Classifications
ICLR 2024Rejected
3
Topology Matters in Fair Graph Learning: a Theoretical Pilot Study
ICLR 2024Rejected
4
Gradient Rewiring for Editable Graph Neural Network Training
NeurIPS 2024Poster
3
On the Equivalence of Graph Convolution and Mixup
ICLR 2024withdrawn