PaperHub

Jun Zhu

~Jun_Zhu2

55
论文总数
27.5
年均投稿
6.1
平均评分
接收情况38/55
会议分布
ICLR
31
NeurIPS
16
ICML
8

发表论文 (55 篇)

202529 篇

6.6
5

ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing

ICLR 2025Poster
4.6
5

When Bigger is Better: Revisiting Large-Batch Optimization in Language Model Pretraining

NeurIPS 2025Rejected
6.3
3

Oscillation-Reduced MXFP4 Training for Vision Transformers

ICML 2025Poster
5.0
3

Zero-shot Quantization for Object Detection

ICLR 2025Rejected
4.0
4

FrameBridge: Improving Image-to-Video Generation with Bridge Models

ICLR 2025Rejected
7.3
4

Audio Super-Resolution with Latent Bridge Models

NeurIPS 2025Poster
7.0
4

SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration

ICLR 2025Poster
3.5
4

LUNCH: Adaptive Balancing of Continual Learning via Hyperparameter Uncertainty

ICLR 2025withdrawn
7.0
6

Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment

ICLR 2025Oral
6.7
3

PivotMesh: Generic 3D Mesh Generation via Pivot Vertices Guidance

ICLR 2025Poster
6.8
4

ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding

NeurIPS 2025Spotlight
7.0
4

Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling

ICLR 2025Poster
6.0
4

Elucidating the Preconditioning in Consistency Distillation

ICLR 2025Poster
4.0
4

SparseDM: Toward Sparse Efficient Diffusion Models

ICLR 2025withdrawn
7.8
5

SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization

ICML 2025Poster
6.6
4

FrameBridge: Improving Image-to-Video Generation with Bridge Models

ICML 2025Poster
6.2
5

Diffusion Bridge Implicit Models

ICLR 2025Poster
6.4
4

A Regularized Newton Method for Nonconvex Optimization with Global and Local Complexity Guarantees

NeurIPS 2025Poster
6.6
4

SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference

ICML 2025Poster
7.2
4

RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers

ICML 2025Poster
6.6
4

Visual Generation Without Guidance

ICML 2025Poster
7.2
4

Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator

ICML 2025Spotlight
7.3
3

On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent

ICLR 2025Spotlight
6.8
4

Scaling Diffusion Transformers Efficiently via $\mu$P

NeurIPS 2025Poster
6.8
4

SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training

NeurIPS 2025Spotlight
5.8
4

ManiBox: Enhancing Spatial Grasping Generalization via Scalable Simulation Data Generation

ICLR 2025Rejected
6.8
4

Robust Representation Consistency Model via Contrastive Denoising

ICLR 2025Poster
7.0
4

RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation

ICLR 2025Poster
8.3
4

STAIR: Improving Safety Alignment with Introspective Reasoning

ICML 2025Oral

202426 篇

5.3
4

S-STE: Continuous Pruning Function for Efficient 2:4 Sparse Pre-training

NeurIPS 2024Poster
6.5
4

Efficient Backpropagation with Variance Controlled Adaptive Sampling

ICLR 2024Poster
3.0
4

Converging and Stabilizing Generative Adversarial Imitation Learning

ICLR 2024Rejected
6.8
4

Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control

NeurIPS 2024Poster
6.2
5

C-GAIL: Stabilizing Generative Adversarial Imitation Learning with Control Theory

NeurIPS 2024Poster
6.3
4

Score Regularized Policy Optimization through Diffusion Behavior

ICLR 2024Poster
6.3
4

Consistency Diffusion Bridge Models

NeurIPS 2024Poster
5.5
4

On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability

NeurIPS 2024Poster
5.0
4

Bridge-TTS: Text-to-Speech Synthesis with Schrodinger Bridge

ICLR 2024withdrawn
5.5
4

Investigating Uncertainty Calibration of Aligned Language Models under the Multiple-Choice Setting

ICLR 2024Rejected
4.0
4

ControlVideo: Conditional Control for Text-driven Video Editing and Beyond

ICLR 2024withdrawn
7.0
4

Rethinking Model Ensemble in Transfer-based Adversarial Attacks

ICLR 2024Poster
6.8
4

Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches

ICLR 2024Poster
5.3
4

BSPA: Exploring Black-box Stealthy Prompt Attacks against Image Generators

ICLR 2024withdrawn
5.0
4

Vidu4D: Single Generated Video to High-Fidelity 4D Reconstruction with Dynamic Gaussian Surfels

NeurIPS 2024Poster
6.8
5

Noise Contrastive Alignment of Language Models with Explicit Rewards

NeurIPS 2024Poster
6.0
4

Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model

NeurIPS 2024Poster
6.5
4

Neural Eigenfunctions Are Structured Representation Learners

ICLR 2024Rejected
5.0
4

Preconditioning for Physics-Informed Neural Networks

ICLR 2024Rejected
5.7
3

PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning

NeurIPS 2024Poster
8.0
3

Robust Classification via a Single Diffusion Model

ICLR 2024Rejected
7.0
4

Diffusion Models are Certifiably Robust Classifiers

NeurIPS 2024Poster
6.3
3

InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image

ICLR 2024Poster
6.0
3

Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection

ICLR 2024Rejected
5.5
4

LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents

ICLR 2024Rejected
5.3
4

PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs

ICLR 2024Rejected
合作者 (20)