2 35

Zhizhou Sha

JamesSand

AI & ML interests

None yet

Recent Activity

upvoted a paper 5 days ago

OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models

upvoted a paper 5 days ago

MAGA: MAssive Genre-Audience Reformulation to Pretraining Corpus Expansion

upvoted a paper 12 days ago

Open Problems in Mechanistic Interpretability

View all activity

Organizations

JamesSand's activity

upvoted 2 papers 5 days ago

OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models

Paper • 2502.01061 • Published 9 days ago • 168

MAGA: MAssive Genre-Audience Reformulation to Pretraining Corpus Expansion

Paper • 2502.04235 • Published 6 days ago • 17

upvoted a paper 12 days ago

Open Problems in Mechanistic Interpretability

Paper • 2501.16496 • Published 15 days ago • 16

upvoted a paper 16 days ago

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Paper • 2501.12948 • Published 21 days ago • 316

upvoted a paper 23 days ago

PaSa: An LLM Agent for Comprehensive Academic Paper Search

Paper • 2501.10120 • Published 26 days ago • 43

authored a paper about 1 month ago

On Computational Limits and Provably Efficient Criteria of Visual Autoregressive Models: A Fine-Grained Complexity Analysis

Paper • 2501.04377 • Published Jan 8 • 14

upvoted a paper about 1 month ago

On Computational Limits and Provably Efficient Criteria of Visual Autoregressive Models: A Fine-Grained Complexity Analysis

Paper • 2501.04377 • Published Jan 8 • 14

commented a paper about 1 month ago

On Computational Limits and Provably Efficient Criteria of Visual Autoregressive Models: A Fine-Grained Complexity Analysis

Paper • 2501.04377 • Published Jan 8 • 14 •

upvoted 3 papers about 1 month ago

MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models

Paper • 2501.02955 • Published Jan 6 • 40

1.58-bit FLUX

Paper • 2412.18653 • Published Dec 24, 2024 • 75

Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Paper • 2412.21187 • Published Dec 30, 2024 • 37

upvoted 2 papers 3 months ago

LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models

Paper • 2411.09595 • Published Nov 14, 2024 • 72

Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning

Paper • 2410.21845 • Published Oct 29, 2024 • 13

upvoted 3 papers 4 months ago

Unbounded: A Generative Infinite Game of Character Life Simulation

Paper • 2410.18975 • Published Oct 24, 2024 • 37

SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree

Paper • 2410.16268 • Published Oct 21, 2024 • 67

Differential Transformer

Paper • 2410.05258 • Published Oct 7, 2024 • 169

upvoted 2 papers 5 months ago

Seed-Music: A Unified Framework for High Quality and Controlled Music Generation

Paper • 2409.09214 • Published Sep 13, 2024 • 52

TokenCompose: Grounding Diffusion with Token-level Supervision

Paper • 2312.03626 • Published Dec 6, 2023 • 5

authored a paper 6 months ago

Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time

Paper • 2408.13233 • Published Aug 23, 2024 • 24

commented a paper 6 months ago

Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time

Paper • 2408.13233 • Published Aug 23, 2024 • 24 •