PaperHub

Yutaka Matsuo

~Yutaka_Matsuo1

26
论文总数
13.0
年均投稿
5.4
平均评分
接收情况12/26
会议分布
ICLR
18
NeurIPS
5
COLM
2
ICML
1

发表论文 (26 篇)

202515 篇

5.3
4

Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks

ICLR 2025Rejected
6.4
4

Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search

NeurIPS 2025Poster
4.0
3

Maximum Likelihood Estimation for Flow Matching by Direct Second-order Trace Objective

ICLR 2025Rejected
4.8
4

ToM-agent: Large Language Models as Theory of Mind Aware Generative Agents with Counterfactual Reflection

ICLR 2025Rejected
5.8
4

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words

ICLR 2025Poster
4.8
4

FullDiffusion: Diffusion Models Without Time Truncation

ICLR 2025Rejected
4.3
4

RAGDP: Retrieve-Augmented Generative Diffusion Policy

ICLR 2025Rejected
6.1
4

Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence

ICML 2025Poster
6.4
4

Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties

NeurIPS 2025Poster
3.5
4

Curse of Instructions: Large Language Models Cannot Follow Multiple Instructions at Once

ICLR 2025Rejected
5.8
4

CityNav: Language-Goal Aerial Navigation Dataset Using Geographic Information

ICLR 2025Rejected
4.5
4

MMA: Benchmarking Multi-Modal Large Language Model in Ambiguity Contexts

ICLR 2025withdrawn
4.8
4

The Geometry of Phase Transitions in Diffusion Models: Tubular Neighbourhoods and Singularities

ICLR 2025Rejected
7.3
4

Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation

NeurIPS 2025Spotlight
5.8
5

Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form

ICLR 2025Poster

202411 篇

6.5
4

Language Model Agents Suffer from Compositional Decision Making

ICLR 2024Rejected
4.2
5

Grokking Tickets: Lottery Tickets Accelerate Grokking

ICLR 2024Rejected
5.0
5

Soft iEP: On the Exploration Inefficacy of Gradient Based Strong Lottery Exploration

ICLR 2024Rejected
6.0
4

Decoupling Noise and Toxic Parameters for Language Model Detoxification by Task Vector Merging

COLM 2024Poster
6.0
5

Geometric-Averaged Preference Optimization for Soft Preference Labels

NeurIPS 2024Poster
6.0
3

Multimodal Web Navigation with Instruction-Finetuned Foundation Models

ICLR 2024Poster
7.3
4

A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis

ICLR 2024Oral
6.3
4

Suspicion Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4

COLM 2024Poster
4.3
4

Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4

ICLR 2024Rejected
5.3
4

ADOPT: Modified Adam Can Converge with the Optimal Rate with Any Hyperparameters

ICLR 2024Rejected
5.5
4

ADOPT: Modified Adam Can Converge with Any $\beta_2$ with the Optimal Rate

NeurIPS 2024Poster
合作者 (20)