Qwen/BlenderWorld
Updated • 2.42k • 23
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Last Secure Code Benchmark: Is the Code You Vibe Secure?
VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs
VoyagerXHF
published a
dataset 3 days ago
VoyagerXHF
updated a
dataset 3 days ago
wutianyi86
submitted a
paper to Daily Papers 4 days ago
Add Agents' Last Exam eval results (24.3 pass rate / 51.2 score, from model card)
#74 opened 6 days ago
by 
SaylorTwift
naykun
updated a
model 6 days ago
yuanfengustc
submitted a
paper to Daily Papers 7 days ago
gradio workflow app
#2 opened 9 days ago
by 
akhaliq
naykun
published a
model 9 days ago
Zhenru
authored 3
papers 9 days ago
RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents
Paper • 2609.22000 • Published • 81
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
Paper • 2609.04148 • Published • 212
Qwen-CUA: Native Computer Use for (almost) Everything
Paper • 2608.02352 • Published • 2
Update README.md
#1 opened 9 days ago
by 
kelseye
Update README.md
#1 opened 9 days ago
by kelseye
yuhao318
authored 6
papers 10 days ago
VLCache: Computing 2% Vision Tokens and Reusing 98% for Vision-Language Inference
Paper • 2512.12977 • Published
Unified Low-rank Compression Framework for Click-through Rate Prediction
Paper • 2405.18146 • Published • 1
H-Scale: Hessian-Guided Scale Refinement for NVFP4 Sub-Byte LLM Inference
Paper • 2608.28113 • Published • 1
Effectively Compress KV Heads for LLM
Paper • 2406.07056 • Published • 1
QUADS: Stabilizing NVFP4 Reinforcement Learning for MoE via QUantization-error Alignment across Dual Sides
Paper • 2607.15810 • Published • 1
TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models
Paper • 2610.07767 • Published • 93
danielhanchen
posted an update 10 days ago
Post
4,898
You can now train your own Decision model like Jev locally!
We increased Qwen3.5 0.8B’s aggregate accuracy from 20.7% to 74.3% across 3 decision benchmarks - on just 4GB VRAM.
Turn any LLM like Qwen3.8, Gemma 4 into decision models with our open-source Unsloth repo.
GitHub: https://github.com/unslothai/unsloth
Guide: https://unsloth.ai/docs/basics/train-your-own-decision-model-with-unsloth
We increased Qwen3.5 0.8B’s aggregate accuracy from 20.7% to 74.3% across 3 decision benchmarks - on just 4GB VRAM.
Turn any LLM like Qwen3.8, Gemma 4 into decision models with our open-source Unsloth repo.
GitHub: https://github.com/unslothai/unsloth
Guide: https://unsloth.ai/docs/basics/train-your-own-decision-model-with-unsloth
- 5 replies