view article Article One Adapter, Both Modalities: Field Notes from Building and Serving a Multimodal Reranker lightonai • 10 days ago • 17
view article Article Bringing Nunchaku 4-bit Diffusion Inference to Diffusers rootonchair, sayakpaul • 4 days ago • 48
MagenticLite Collection An open-source agentic app that runs browser and file tasks on small models. • 2 items • Updated 4 days ago • 9
view article Article Fine-tune video and image models at scale with NVIDIA NeMo Automodel and 🤗 Diffusers nvidia • 9 days ago • 79
τ^2-Bench: Evaluating Conversational Agents in a Dual-Control Environment Paper • 2506.07982 • Published Jun 9, 2025 • 8
view article Article NVIDIA Nemotron 3 Embed Ranks #1 Overall on RTEB, Advancing Agentic Retrieval nvidia • 10 days ago • 57
Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models Paper • 2607.08317 • Published 18 days ago • 35
KronQ: LLM Quantization via Kronecker-Factored Hessian Paper • 2607.07964 • Published 19 days ago • 32
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation Paper • 2607.05147 • Published 21 days ago • 37
TurboServe: Serving Streaming Video Generation Efficiently and Economically Paper • 2606.19271 • Published Jun 17 • 37
ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes Paper • 2607.04439 • Published 22 days ago • 62
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation Paper • 2607.05382 • Published 18 days ago • 87
ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory Paper • 2607.10350 • Published 12 days ago • 85
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling Paper • 2607.02980 • Published 24 days ago • 81
Weak-to-Strong Generalization via Direct On-Policy Distillation Paper • 2607.05394 • Published 19 days ago • 138
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable Paper • 2607.13285 • Published 13 days ago • 225