PaperHub

Jinwoo Shin

~Jinwoo_Shin1

34
论文总数
17.0
年均投稿
6.2
平均评分
接收情况28/34
会议分布
ICLR
18
NeurIPS
11
ICML
4
COLM
1

发表论文 (34 篇)

202517 篇

6.8
4

Track3R: Joint Point Map and Trajectory Prior for Spatiotemporal 3D Understanding

NeurIPS 2025Poster
8.7
3

Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment

ICLR 2025Oral
6.8
4

Self-Refining Language Model Anonymizers via Adversarial Distillation

NeurIPS 2025Poster
6.1
4

Test-Time Adaptation with Binary Feedback

ICML 2025Poster
4.8
3

ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification

ICML 2025Poster
5.5
4

Debiasing Online Preference Learning via Preference Feature Preservation

ICLR 2025Rejected
7.8
4

MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement

NeurIPS 2025Poster
6.0
5

Binary-Feedback Active Test-Time Adaptation

ICLR 2025Rejected
6.7
3

Controllable Blur Data Augmentation Using 3D-Aware Motion Estimation

ICLR 2025Poster
6.2
5

Subtask-Aware Visual Reward Learning from Segmented Demonstrations

ICLR 2025Poster
6.5
4

Learning to Contextualize Web Pages for Enhanced Decision Making by LLM Agents

ICLR 2025Poster
6.0
4

Compress, Gather, and Recompute: REFORMing Long-Context Processing in Transformers

NeurIPS 2025Poster
5.5
4

PRIME: Deep Imbalanced Regression with Proxies

ICML 2025Poster
6.0
4

DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing

ICLR 2025Poster
6.4
4

Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics

NeurIPS 2025Poster
9.0
6

Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

ICLR 2025Oral
4.9
4

Peri-LN: Revisiting Normalization Layer in the Transformer Architecture

ICML 2025Poster

202417 篇

6.3
4

DreamFlow: High-quality text-to-3D generation by Approximating Probability Flow

ICLR 2024Spotlight
6.5
4

ReMoDetect: Reward Models Recognize Aligned LLM's Generations

NeurIPS 2024Poster
5.7
3

NeFL: Nested Federated Learning for Heterogeneous Clients

ICLR 2024Rejected
3.7
3

InstaTAP: Instance Motion Estimation for Tracking Any Point

ICLR 2024withdrawn
5.5
4

Online Adaptation of Language Models with a Memory of Amortized Contexts

NeurIPS 2024Poster
5.8
4

Direct Consistency Optimization for Robust Customization of Text-to-Image Diffusion models

NeurIPS 2024Poster
7.5
4

Querying Easily Flip-flopped Samples for Deep Active Learning

ICLR 2024Poster
5.3
3

HFDream: Improving 3D Generation via Human-Assisted Multi-view Text-to-Image Models

ICLR 2024Rejected
7.0
4

Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition

ICLR 2024Poster
5.8
4

Data-Efficient Molecular Generation with Hierarchical Textual Inversion

ICLR 2024Rejected
6.0
3

Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models

ICLR 2024Poster
6.3
3

TrackIME: Enhanced Video Point Tracking via Instance Motion Estimation

NeurIPS 2024Spotlight
4.8
4

Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning

NeurIPS 2024Poster
6.3
4

Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs

ICLR 2024Poster
6.4
5

SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs

ICLR 2024Poster
6.5
4

Conditional Synthesis of 3D Molecules with Time Correction Sampler

NeurIPS 2024Poster
6.3
4

Tabular Transfer Learning via Prompting LLMs

COLM 2024Poster
合作者 (20)