Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation
Paper • 2602.12125 • Published • 60 •
3
Grant Singleton
grantsing
AI & ML interests
Computer vision, robotics, LLMs
Recent Activity
commentedon a paper about 4 hours ago
Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation commentedon a paper about 4 hours ago
OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens commentedon a paper about 4 hours ago
Utonia: Toward One Encoder for All Point CloudsOrganizations
None yet
commented 5
papers about 4 hours ago
OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens
Paper • 2603.02138 • Published • 147 •
5
Utonia: Toward One Encoder for All Point Clouds
Paper • 2603.03283 • Published • 183 •
4
UniG2U-Bench: Do Unified Models Advance Multimodal Understanding?
Paper • 2603.03241 • Published • 86 •
4
On Data Engineering for Scaling LLM Terminal Capabilities
Paper • 2602.21193 • Published • 99 •
4
commented 5
papers 1 day ago
MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models
Paper • 2602.17602 • Published • 56 •
4
From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models
Paper • 2602.22859 • Published • 151 •
4
The Trinity of Consistency as a Defining Principle for General World Models
Paper • 2602.23152 • Published • 199 •
5
DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference
Paper • 2602.21548 • Published • 47 •
5
Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter
Paper • 2511.16665 • Published •
1
commented 5
papers 2 days ago
dLLM: Simple Diffusion Language Modeling
Paper • 2602.22661 • Published • 149 •
6
SkillOrchestra: Learning to Route Agents via Skill Transfer
Paper • 2602.19672 • Published • 56 •
6
OmniGAIA: Towards Native Omni-Modal AI Agents
Paper • 2602.22897 • Published • 53 •
4
From Scale to Speed: Adaptive Test-Time Scaling for Image Editing
Paper • 2603.00141 • Published • 138 •
5
Heterogeneous Agent Collaborative Reinforcement Learning
Paper • 2603.02604 • Published • 188 •
7
commented 5
papers 3 days ago
RubricBench: Aligning Model-Generated Rubrics with Human Standards
Paper • 2603.01562 • Published • 60 •
4
Beyond Language Modeling: An Exploration of Multimodal Pretraining
Paper • 2603.03276 • Published • 100 •
6
Helios: Real Real-Time Long Video Generation Model
Paper • 2603.04379 • Published • 174 •
6
Qwen3-Coder-Next Technical Report
Paper • 2603.00729 • Published • 60 •
5
Interactive Benchmarks
Paper • 2603.04737 • Published • 18 •
10