AGI Lab

non-profit

Activity Feed Request to join this org

AI & ML interests

None defined yet.

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

Lucifer744

authored 6 papers 3 days ago

High-Quality Real-Time Rendering Using Subpixel Sampling Reconstruction

Paper • 2301.01036 • Published Jun 25, 2023

Detachable Novel Views Synthesis of Dynamic Scenes Using Distribution-Driven Neural Radiance Fields

Paper • 2301.00411 • Published Jan 11, 2023

Auto-Encoding Score Distribution Regression for Action Quality Assessment

Paper • 2111.11029 • Published Aug 31, 2022

TSGate: Timestep-Aware Gated Attention for Diffusion Transformers

Paper • 2609.34539 • Published 21 days ago

SAGE: Subspace Alignment for Classifier-Free Guidance in Mixture-of-Experts Diffusion Models

Paper • 2609.34525 • Published 21 days ago

KiT: A Foundation Model for Financial Time-Series Forecasting using DiffusionTransformers

Paper • 2609.34507 • Published 21 days ago

CokeWang

posted an update about 1 month ago

Post

LoopArena: Which Models Make Good Runtime Controllers for Coding Agents?

Long-running coding agents are often guided by another model that reviews progress, chooses the next assignment, requests verification, and decides when to stop. LoopArena evaluates that model as the Controller while keeping the coding Worker and execution setup fixed.
The benchmark covers next-step decisions, repeated control over task slices, and complete software tasks. We have released the benchmark data, evaluation code, and v0.1.0 results.

LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering (2608.28281)
https://github.com/AMAP-ML/LoopArena