Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention
Paper • 2605.29548 • Published • 3
Electronicarts
company
Verified
AI & ML interests
None defined yet.
Recent Activity
View all activity
taesiri
submitted a
paper to Daily Papers about 12 hours ago
taesiri
submitted 4
papers to Daily Papers about 13 hours ago
WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction
Paper • 2605.29341 • Published • 3
minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models
Paper • 2605.30263 • Published • 36
NeuROK: Generative 4D Neural Object Kinematics
Paper • 2605.30347 • Published • 3
Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments
Paper • 2605.30280 • Published • 60
taesiri
submitted 5
papers to Daily Papers 1 day ago
PEAM: Parametric Embodied Agent Memory through Contrastive Internalization of Experience in Minecraft
Paper • 2605.27762 • Published
Agent Explorative Policy Optimization for Multimodal Agentic Reasoning
Paper • 2605.28774 • Published • 76
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
Paper • 2605.28816 • Published • 228
AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
Paper • 2605.28655 • Published • 4
CubePart: An Open-Vocabulary Part-Controllable 3D Generator
Paper • 2605.28763 • Published • 11
taesiri
submitted 5
papers to Daily Papers 3 days ago
MRT: Masked Region Transformer for Layered Image Generation and Editing at Scale
Paper • 2605.27235 • Published • 5
The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
Paper • 2605.26494 • Published • 31
Negligible in Size, Significant in Effect: On Scale Vectors in Large Language Models
Paper • 2605.26895 • Published • 15
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
Paper • 2605.27365 • Published • 115
MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation
Paper • 2605.27366 • Published • 18
taesiri
submitted 5
papers to Daily Papers 5 days ago
GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction
Paper • 2605.23888 • Published • 11
LLMs as Noisy Channels: A Shannon Perspective on Model Capacity and Scaling Laws
Paper • 2605.23901 • Published • 11
From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills
Paper • 2605.23899 • Published • 28
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Paper • 2605.23904 • Published • 200
PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion
Paper • 2605.23902 • Published • 40