Starstrek

Stars321123's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 3 papers about 17 hours ago

Physical Simulator In-the-Loop Video Generation

Paper • 2603.06408 • Published 5 days ago • 10

Dynamic Chunking Diffusion Transformer

Paper • 2603.06351 • Published 5 days ago • 12

WildActor: Unconstrained Identity-Preserving Video Generation

Paper • 2603.00586 • Published 11 days ago • 30

upvoted 4 collections about 18 hours ago

Openhands Trajectories

Collection

Dataset of 67,074 OpenHands trajectories collected with Qwen3-Coder-480B-A35B-Instruct and two RFT checkpoints trained on the data • 3 items • Updated Dec 23, 2025 • 7

LK-Speculators

Collection

High-performance speculative decoding draft models trained using LK losses, a novel training objectives that directly optimize acceptance rate • 9 items • Updated 8 days ago • 5

Infinity-Instruct-Completions

Collection

Training data for speculative decoding draft models, containing model-generated responses for 660K prompts from Infinity-Instruct-0625. • 6 items • Updated 9 days ago • 3

SWE-rebench-V2

Collection

SWE-rebench-V2 is a curated dataset of software-engineering tasks derived from real GitHub issues and pull requests. • 3 items • Updated 8 days ago • 6

liked a model about 19 hours ago

replit/replit-code-v1-3b

Text Generation • Updated Jul 21, 2023 • 378 • 742

upvoted a paper about 19 hours ago

Scale Space Diffusion

Paper • 2603.08709 • Published 1 day ago • 9

liked 2 models about 20 hours ago

HauhauCS/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive

4B • Updated 7 days ago • 55.5k • 91

HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive

9B • Updated 7 days ago • 127k • 314

upvoted a paper about 20 hours ago

Lost in Stories: Consistency Bugs in Long Story Generation by LLMs

Paper • 2603.05890 • Published 5 days ago • 75

upvoted a paper about 21 hours ago

π-StepNFT: Wider Space Needs Finer Steps in Online RL for Flow-based VLAs

Paper • 2603.02083 • Published 9 days ago • 9

upvoted 2 papers 2 days ago

SageBwd: A Trainable Low-bit Attention

Paper • 2603.02170 • Published 9 days ago • 16

Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders

Paper • 2603.06569 • Published 5 days ago • 95

upvoted 2 papers 3 days ago

SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion

Paper • 2503.11576 • Published Mar 14, 2025 • 154

MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier

Paper • 2603.03756 • Published 7 days ago • 85

upvoted a collection 3 days ago

To read

Collection

140 items • Updated 2 days ago • 4

upvoted a paper 3 days ago

Heterogeneous Agent Collaborative Reinforcement Learning

Paper • 2603.02604 • Published 8 days ago • 161

liked a Space 4 days ago

Running on Zero

Featured

74

LTX 2.3 Distilled

📚

74

Generate cinematic videos with audio from text prompts