Garry Osborne

garryo's activity

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

upvoted a paper 3 days ago

From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents

Paper • 2603.22386 • Published 5 days ago • 51

upvoted 10 papers 9 days ago

LaDe: Unified Multi-Layered Graphic Media Generation and Decomposition

Paper • 2603.17965 • Published 10 days ago • 6

Unified Spatio-Temporal Token Scoring for Efficient Video VLMs

Paper • 2603.18004 • Published 10 days ago • 12

Stereo World Model: Camera-Guided Stereo Video Generation

Paper • 2603.17375 • Published 10 days ago • 11

AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents

Paper • 2603.16496 • Published 11 days ago • 13

LoST: Level of Semantics Tokenization for 3D Shapes

Paper • 2603.17995 • Published 10 days ago • 31

Temporal Gains, Spatial Costs: Revisiting Video Fine-Tuning in Multimodal Large Language Models

Paper • 2603.17541 • Published 10 days ago • 20

Look Before Acting: Enhancing Vision Foundation Representations for Vision-Language-Action Models

Paper • 2603.15618 • Published 12 days ago • 21

MosaicMem: Hybrid Spatial Memory for Controllable Video World Models

Paper • 2603.17117 • Published 11 days ago • 87

Video-CoE: Reinforcing Video Event Prediction via Chain of Events

Paper • 2603.14935 • Published 12 days ago • 91

MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild

Paper • 2603.17187 • Published 11 days ago • 132

upvoted 3 papers 10 days ago

FinToolBench: Evaluating LLM Agents for Real-World Financial Tool Use

Paper • 2603.08262 • Published 19 days ago • 42

TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas

Paper • 2603.16448 • Published 11 days ago • 58

InCoder-32B: Code Foundation Model for Industrial Scenarios

Paper • 2603.16790 • Published 11 days ago • 302

upvoted 2 papers 11 days ago

Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training

Paper • 2603.12255 • Published 16 days ago • 90

ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation

Paper • 2603.11421 • Published 16 days ago • 34

upvoted a paper 22 days ago

DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval

Paper • 2603.04743 • Published 23 days ago • 52

upvoted 3 papers about 1 month ago

VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training

Paper • 2602.10693 • Published Feb 11 • 220

Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents

Paper • 2602.16855 • Published Feb 15 • 50

SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning

Paper • 2602.13515 • Published Feb 13 • 44