SkyReels-V4: Multi-modal Video-Audio Generation, Inpainting and Editing model
Paper • 2602.21818 • Published • 56 •
8
Grant Singleton
grantsing
AI & ML interests
Computer vision, robotics, LLMs
Recent Activity
commentedon a paper about 10 hours ago
SkyReels-V4: Multi-modal Video-Audio Generation, Inpainting and Editing model commentedon a paper about 10 hours ago
MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios commentedon a paper about 10 hours ago
Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics ModelingOrganizations
None yet
commented 6
papers about 10 hours ago
MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios
Paper • 2602.22638 • Published • 107 •
4
Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling
Paper • 2603.04553 • Published • 3 •
3
BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?
Paper • 2603.03194 • Published • 56 •
6
BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?
Paper • 2603.03194 • Published • 56 •
6
MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier
Paper • 2603.03756 • Published • 89 •
6
commented 5
papers 1 day ago
SkillNet: Create, Evaluate, and Connect AI Skills
Paper • 2603.04448 • Published • 88 •
6
Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders
Paper • 2603.06569 • Published • 113 •
5
WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching
Paper • 2603.06331 • Published • 3 •
3
$\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space
Paper • 2603.04948 • Published • 1 •
3
DreamCAD: Scaling Multi-modal CAD Generation using Differentiable Parametric Surfaces
Paper • 2603.05607 • Published • 3 •
3
commented 5
papers 2 days ago
Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigation
Paper • 2602.05827 • Published • 17 •
3
DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation
Paper • 2602.12160 • Published • 38 •
5
Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks
Paper • 2602.14689 • Published • 1 •
3
Think Deep, Not Just Long: Measuring LLM Reasoning Effort via Deep-Thinking Tokens
Paper • 2602.13517 • Published • 2 •
2
Learning Personalized Agents from Human Feedback
Paper • 2602.16173 • Published • 9 •
3
commented 4
papers 3 days ago
Lost in Stories: Consistency Bugs in Long Story Generation by LLMs
Paper • 2603.05890 • Published • 90 •
5
Real Money, Fake Models: Deceptive Model Claims in Shadow APIs
Paper • 2603.01919 • Published • 2 •
1
Believe Your Model: Distribution-Guided Confidence Calibration
Paper • 2603.03872 • Published • 39 •
4
How Far Can Unsupervised RLVR Scale LLM Training?
Paper • 2603.08660 • Published • 56 •
4