ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
Paper • 2609.14857 • Published • 215
Aisha Al-Rashid
scroll-lover
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 23 days ago
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement upvoted a paper 27 days ago
Dream-RSI: Recursive Self-Improvement through Evolving Worlds liked a model 28 days ago
khazic/tfm-offline-stage1-group-6Organizations
None yet
upvoted a paper 23 days ago
upvoted a paper 27 days ago
upvoted a paper 29 days ago
upvoted 3
papers about 1 month ago
Ring Forcing: Towards Precise Long-Term Memory for Autoregressive Video Diffusion
Paper • 2608.26794 • Published • 16
StudentSim: Training LLM-based Student Simulators
Paper • 2609.01591 • Published • 479
Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling
Paper • 2608.30821 • Published • 69
upvoted 3
papers about 2 months ago
HarnessEval-W: Agentifying the Evaluation of Visual Worlds
Paper • 2608.16859 • Published • 122
Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization
Paper • 2608.16072 • Published • 52
Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill
Paper • 2608.11924 • Published • 111
upvoted 5
papers 2 months ago
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA
Paper • 2608.09819 • Published • 181
πR^2: Reactive Real-time Flow Policies
Paper • 2607.26055 • Published • 6
TARS: Timestep-Aware Data Scaling for 3D-Free Video Re-Shooting
Paper • 2607.28261 • Published • 18
Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents
Paper • 2607.28227 • Published • 159
Scaling Native Multimodal Pre-Training From Scratch
Paper • 2607.22043 • Published • 30
upvoted 5
papers 3 months ago
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable
Paper • 2607.13285 • Published • 126
Multi-Turn Agentic Scientific Literature Search via Workflow Induction
Paper • 2607.00597 • Published • 28
Teaching LLMs to Recommend and Defer in Underrepresented Epilepsy Care
Paper • 2606.31036 • Published • 6
PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation
Paper • 2607.03068 • Published • 4
One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining
Paper • 2606.30634 • Published • 24
upvoted a paper 4 months ago