·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
SFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning38m◆Optical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning38m◆Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models38m◆Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents38m◆Why Muon Outperforms Adam: A Curvature Perspective38m◆Provably Auditable and Safe LLM Agents from Human-Authored Ontologies38m◆q0: Primitives for Hyper-Epoch Pretraining38m◆Formal Semantics for Agentic Tool Protocols: A Process Calculus Approach38m◆Proof-Carrying Agent Actions: Model-Agnostic Runtime Governance for Heterogeneous Agent Systems38m◆SymTRELLIS: Symmetry-Enforced Voxel Latents for 3D Generation38m◆AgenticDiffusion: Agentic Diffusion-based Path Planning for Vision-Based UAV Navigation38m◆Widening the Gap: Exploiting LLM Quantization via Outlier Injection38m◆Evaluating Zero-Shot and One-Shot Adaptation of Small Language Models in Leader-Follower Interaction38m◆SaliMory: Orchestrating Cognitive Memory for Conversational Agents38m◆Optimizing Explicit Unit-Distance Lower-Bound Certificates38m◆MedForge: Interpretable Medical Deepfake Detection via Forgery-aware Reasoning38m◆Demystifying Multi-Agent Debate: The Role of Confidence and Diversity38m◆Physics-Informed Machine Learning for Short-Term Flood Prediction38m◆Beyond Objective Equivalence: Constraint Injection for LLM-Based Optimization Modeling on Vehicle Routing Problems38m◆POLARIS: Guiding Small Models to Write Long Stories38m◆SFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning38m◆Optical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning38m◆Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models38m◆Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents38m◆Why Muon Outperforms Adam: A Curvature Perspective38m◆Provably Auditable and Safe LLM Agents from Human-Authored Ontologies38m◆q0: Primitives for Hyper-Epoch Pretraining38m◆Formal Semantics for Agentic Tool Protocols: A Process Calculus Approach38m◆Proof-Carrying Agent Actions: Model-Agnostic Runtime Governance for Heterogeneous Agent Systems38m◆SymTRELLIS: Symmetry-Enforced Voxel Latents for 3D Generation38m◆AgenticDiffusion: Agentic Diffusion-based Path Planning for Vision-Based UAV Navigation38m◆Widening the Gap: Exploiting LLM Quantization via Outlier Injection38m◆Evaluating Zero-Shot and One-Shot Adaptation of Small Language Models in Leader-Follower Interaction38m◆SaliMory: Orchestrating Cognitive Memory for Conversational Agents38m◆Optimizing Explicit Unit-Distance Lower-Bound Certificates38m◆MedForge: Interpretable Medical Deepfake Detection via Forgery-aware Reasoning38m◆Demystifying Multi-Agent Debate: The Role of Confidence and Diversity38m◆Physics-Informed Machine Learning for Short-Term Flood Prediction38m◆Beyond Objective Equivalence: Constraint Injection for LLM-Based Optimization Modeling on Vehicle Routing Problems38m◆POLARIS: Guiding Small Models to Write Long Stories38m◆
News/Tail-Aware HiFloat4: W4A4 Post-Training Quantization for Wan2.2
arxiv
PublishedMay 27, 2026 at 4:00 AM

Tail-Aware HiFloat4: W4A4 Post-Training Quantization for Wan2.2

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2605.26628v1 Announce Type: new Abstract: This report describes Tail-Aware HiFloat4, our submission to the low-bit text-to-video generation quantization challenge. Our method adapts the public ViDiT-Q post-training quantization pipeline to Wan2.2 under the HiFloat4 numerical format. We quantiz

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivSFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning38marxivOptical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning38marxivDynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models38marxivTemporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents38m
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews