AGI Lab

non-profit

AI & ML interests

None defined yet.

Recent Activity

Lutalica authored a paper about 2 months ago

Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI Agents

Lutalica authored a paper 2 months ago

D-CORE: Incentivizing Task Decomposition in Large Reasoning Models for Complex Tool Use

Lutalica authored a paper 2 months ago

Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization

View all activity

Papers

How LoRA Remembers? A Parametric Memory Law for LLM Finetuning

MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems

View all Papers

authored 2 papers about 10 hours ago

Oxygen-TryOn: Fashion-Native Foundation Model for Any-item Virtual Try-On

Paper • 2607.21694 • Published 6 days ago • 20

RePainter: Empowering E-commerce Object Removal via Spatial-matting Reinforcement Learning

Paper • 2510.07721 • Published Oct 9, 2025 • 9

submitted 3 papers to Daily Papers 2 months ago

How LoRA Remembers? A Parametric Memory Law for LLM Finetuning

Paper • 2605.30260 • Published May 28 • 44

Rethinking Memory as Continuously Evolving Connectivity

Paper • 2605.28773 • Published May 27 • 34

MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems

Paper • 2605.28732 • Published May 27 • 40

submitted a paper to Daily Papers 2 months ago

Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization

Paper • 2605.28109 • Published May 27 • 23

xiaochonglinghu

submitted a paper to Daily Papers 2 months ago

Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos

Paper • 2605.18233 • Published May 18 • 93

submitted a paper to Daily Papers 2 months ago

FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization

Paper • 2605.15824 • Published May 15 • 67

submitted a paper to Daily Papers 2 months ago

BEAM: Binary Expert Activation Masking for Dynamic Routing in MoE

Paper • 2605.14438 • Published May 14 • 5

authored a paper 3 months ago

What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion

Paper • 2605.07915 • Published May 8 • 9

submitted a paper to Daily Papers 3 months ago

What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion

Paper • 2605.07915 • Published May 8 • 9

authored 9 papers 3 months ago

MUSES: 3D-Controllable Image Generation via Multi-Modal Agent Collaboration

Paper • 2408.10605 • Published Aug 20, 2024 • 2

TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning

Paper • 2410.19702 • Published Oct 25, 2024 • 2

VideoChat-A1: Thinking with Long Videos by Chain-of-Shot Reasoning

Paper • 2506.06097 • Published Jun 6, 2025 • 1

LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents

Paper • 2503.10200 • Published Mar 13, 2025

VideoChat-R1.5: Visual Test-Time Scaling to Reinforce Multimodal Reasoning by Iterative Perception

Paper • 2509.21100 • Published Sep 25, 2025 • 1

UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation

Paper • 2510.10575 • Published Oct 12, 2025 • 2

Beyond Textual CoT: Interleaved Text-Image Chains with Deep Confidence Reasoning for Image Editing

Paper • 2510.08157 • Published Oct 9, 2025

VideoChat-M1: Collaborative Policy Planning for Video Understanding via Multi-Agent Reinforcement Learning

Paper • 2511.19524 • Published Nov 24, 2025

Continuous-Time Distribution Matching for Few-Step Diffusion Distillation

Paper • 2605.06376 • Published May 7 • 27