GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction
Paper • 2605.23888 • Published • 2
AI & ML interests
None defined yet.
Recent Activity
View all activity
taesiri
submitted 5
papers to Daily Papers about 13 hours ago
LLMs as Noisy Channels: A Shannon Perspective on Model Capacity and Scaling Laws
Paper • 2605.23901 • Published • 7
From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills
Paper • 2605.23899 • Published • 20
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Paper • 2605.23904 • Published • 146
PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion
Paper • 2605.23902 • Published • 17
taesiri
submitted 5
papers to Daily Papers 4 days ago
From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning
Paper • 2605.22074 • Published • 2
Bernini: Latent Semantic Planning for Video Diffusion
Paper • 2605.22344 • Published • 7
TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks
Paper • 2605.22535 • Published • 6
Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement Learning
Paper • 2605.22642 • Published • 33
Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention
Paper • 2605.22791 • Published • 23
taesiri
submitted 5
papers to Daily Papers 5 days ago
DrawMotion: Generating 3D Human Motions by Freehand Drawing
Paper • 2605.20955 • Published • 3
PlanningBench: Generating Scalable and Verifiable Planning Data for Evaluating and Training Large Language Models
Paper • 2605.20873 • Published • 4
SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents
Paper • 2605.21384 • Published • 4
Mem-π: Adaptive Memory through Learning When and What to Generate
Paper • 2605.21463 • Published • 5
Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning
Paper • 2605.21487 • Published • 21
taesiri
submitted 5
papers to Daily Papers 6 days ago
Delta Attention Residuals
Paper • 2605.18855 • Published • 8
SceneCode: Executable World Programs for Editable Indoor Scenes with Articulated Objects
Paper • 2605.19587 • Published
OpenComputer: Verifiable Software Worlds for Computer-Use Agents
Paper • 2605.19769 • Published • 57
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration
Paper • 2605.20025 • Published • 179
Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding
Paper • 2605.20104 • Published • 7