PaperHub

Kaipeng Zhang

~Kaipeng_Zhang1

31
论文总数
15.5
年均投稿
5.4
平均评分
接收情况14/31
会议分布
ICLR
22
NeurIPS
7
ICML
2

发表论文 (31 篇)

202519 篇

4.8
4

Improving Autoregressive Image Generation by Mitigating Gradient Bias in Softmax

ICLR 2025withdrawn
7.5
4

Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language Bootstrapping

ICLR 2025Oral
4.7
3

TP-Eval: Tap Multimodal LLMs' Potential in Evaluation by Customizing Prompts

ICLR 2025Rejected
4.0
4

ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification and KV Cache Compression

ICLR 2025withdrawn
4.5
4

HRVMamba: High-Resolution Visual State Space Model for Dense Prediction

ICLR 2025withdrawn
5.2
5

Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation

ICLR 2025Rejected
5.5
4

ZipAR: Parallel Autoregressive Image Generation through Spatial Locality

ICML 2025Poster
4.8
4

Diffree: Text-Guided Shape Free Object Inpainting with Diffusion Model

ICLR 2025Rejected
3.0
3

EfficientQAT: Efficient Quantization-Aware Training for Large Language Models

ICLR 2025Rejected
6.6
4

Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation

ICML 2025Poster
6.0
4

LLaMA Decoder As Vision Transformer

ICLR 2025Rejected
7.3
4

To Think or Not To Think: A Study of Thinking in Rule-Based Visual Reinforcement Fine-Tuning

NeurIPS 2025Spotlight
4.5
4

Simple and Fast CNN for Vision

ICLR 2025Rejected
3.5
4

MatchMask: Mask-Centric Generative Data Augmentation for Label-Scarce Semantic Segmentation

ICLR 2025withdrawn
6.0
4

SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement

ICLR 2025Poster
5.0
4

Prioritize Alignment in Dataset Distillation

ICLR 2025Rejected
6.4
4

REPA Works Until It Doesn’t: Early-Stopped, Holistic Alignment Supercharges Diffusion Training

NeurIPS 2025Poster
6.0
5

MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models

ICLR 2025Poster
6.8
4

Neural-Driven Image Editing

NeurIPS 2025Poster

202412 篇

5.0
5

Language-driven Open-Vocabulary Keypoint Detection for Animal Body and Face

ICLR 2024withdrawn
4.6
5

Meta-Transformer: A Unified Framework for Multimodal Learning

ICLR 2024withdrawn
4.7
3

Towards Unified and Effective Domain Generalization

ICLR 2024withdrawn
7.0
4

BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation

ICLR 2024Poster
7.0
4

Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching

ICLR 2024Poster
4.8
4

CTRL: Graph condensation via crafting rational trajectory matching

ICLR 2024Rejected
5.3
3

Prioritize Alignment in Dataset Distillation

NeurIPS 2024Rejected
5.0
4

Simple CNN for Vision

ICLR 2024Rejected
6.4
5

OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models

ICLR 2024Spotlight
5.7
3

SearchLVLMs: A Plug-and-Play Framework for Augmenting Large Vision-Language Models by Searching Up-to-Date Internet Knowledge

NeurIPS 2024Poster
5.3
4

Rethinking Human Evaluation Protocol for Text-to-Video Models: Enhancing Reliability, Reproducibility, and Practicality

NeurIPS 2024Poster
5.2
5

Lumina-Next : Making Lumina-T2X Stronger and Faster with Next-DiT

NeurIPS 2024Poster
合作者 (20)