MoLeMo Lab

non-profit

https://www.molemo.org

AI & ML interests

None defined yet.

Recent Activity

Duke-de-Artois authored a paper about 1 hour ago

Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models

Duke-de-Artois authored a paper about 1 hour ago

Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction

Duke-de-Artois authored a paper about 1 hour ago

TurboClear: One-Step Object-Effect Removal via Region-Calibrated Distribution Matching and Fusion

View all activity

authored 3 papers about 1 hour ago

Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models

Paper • 2609.34972 • Published 8 days ago • 30

Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction

Paper • 2609.32353 • Published 10 days ago • 8

TurboClear: One-Step Object-Effect Removal via Region-Calibrated Distribution Matching and Fusion

Paper • 2608.01288 • Published Aug 2

submitted a paper to Daily Papers 7 days ago

Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction

Paper • 2609.32353 • Published 10 days ago • 8

authored a paper about 2 months ago

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA

Paper • 2608.09819 • Published Aug 10 • 180

authored a paper 3 months ago

LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget

Paper • 2607.14952 • Published Jul 16 • 92

authored 2 papers 5 months ago

MinT: Managed Infrastructure for Training and Serving Millions of LLMs

Paper • 2605.13779 • Published May 13 • 227

$δ$-mem: Efficient Online Memory for Large Language Models

Paper • 2605.12357 • Published May 12 • 133

authored a paper 5 months ago

$δ$-mem: Efficient Online Memory for Large Language Models

Paper • 2605.12357 • Published May 12 • 133

authored a paper 7 months ago

SlowBA: An efficiency backdoor attack towards VLM-based GUI agents

Paper • 2603.08316 • Published Mar 9 • 1

submitted a paper to Daily Papers 7 months ago

SlowBA: An efficiency backdoor attack towards VLM-based GUI agents

Paper • 2603.08316 • Published Mar 9 • 1

authored a paper 8 months ago

PlanViz: Evaluating Planning-Oriented Image Generation and Editing for Computer-Use Tasks

Paper • 2602.06663 • Published Feb 6 • 5

submitted a paper to Daily Papers 8 months ago

PlanViz: Evaluating Planning-Oriented Image Generation and Editing for Computer-Use Tasks

Paper • 2602.06663 • Published Feb 6 • 5

authored 3 papers 8 months ago

NVIDIA Nemotron Nano V2 VL

Paper • 2511.03929 • Published Nov 6, 2025 • 32

AgentDevel: Reframing Self-Evolving LLM Agents as Release Engineering

Paper • 2601.04620 • Published Jan 8 • 3

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

Paper • 2601.22975 • Published Jan 30 • 113

posted an update 8 months ago

Post

2317

From Pointers to Footnotes: Why Agents will be “Reference-First”

https://medium.com/@di-zhang-fdu/from-pointers-to-footnotes-why-agents-will-be-reference-first-88d0e9730e37

posted an update 9 months ago

Post

559

AgentDevel: Reframing Self-Evolving LLM Agents as Release Engineering
Improve your agent like Software Engineers, Driven by test and statistical information.
https://www.arxiv.org/abs/2601.04620

submitted a paper to Daily Papers 9 months ago

AgentDevel: Reframing Self-Evolving LLM Agents as Release Engineering

Paper • 2601.04620 • Published Jan 8 • 3

posted an update 9 months ago

Post

349

On the eve of the birth of the Vibe Computer: Why agentic coding feels like a 1980s terminal — and why that’s the point
https://di-zhang-fdu.medium.com/on-the-eve-of-the-birth-of-the-vibe-computer-why-agentic-coding-feels-like-a-1980s-terminal-and-96c41510c356

2 replies

·