arXiv
Verdict: NotableWeVisOne-VL: Unified Visual Perception from Objects to Pixels
Existing vision-language models (VLMs) remain unreliable for fine-grained visual perception.
- HF ▲ 223
- Stars ★ 78
Artificial Intelligence
Models, methods, and the machinery of intelligence.
Edition No. 26
Updated UTC
Top stories
1. Ropedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience
World models enable embodied agents to anticipate action consequences, yet jointly modeling locomotion and manipulation across diverse embodiments remains challenging due to heterogeneous action spaces and limited…
Verdict: Notable██████░░░░5.72. Deep Search in Real-World Web Environments
Despite substantial progress in Deep Search agents, their ability to conduct end-to-end research in real-world open Web environments remains insufficiently evaluated.
Verdict: Notable██████░░░░5.6
More top stories
- arXivby Zhou, Yang, Sun +8
OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory
Multimodal large language models (MLLMs) have made rapid progress on visual reasoning, yet many tasks require evidence that is difficult to obtain through internal reasoning alone: our ....
No.03Verdict: NotableScore██████░░░░5.6 - arXivby Zhuang, Lei, Su +7
DecisionPivot: A Diagnostic Benchmark for Decision Models in LLM Systems
Decision models support routing, guardrails, and output verification in LLM systems.
No.04Verdict: NotableScore██████░░░░5.6 - Hugging Faceby Fang, Qian, Lu +6
SolarRenderer: Few-Step Generative Reference Rendering
Game engines and coding agents can specify the layout, motion, and camera of a scene, yet turning such coarse structure into realistic video requires a renderer that follows the structure ....
No.05Verdict: NotableScore██████░░░░5.6 - arXivby Levy, Shlomov, Choshen
Retrieval Augmented Generation Compositionality
Retrieval Augmented Generation (RAG) grounds large language models in external knowledge.
No.06Verdict: NotableScore█████░░░░░5.3 - arXivby Nguyen, Hu, Anbalagan +155
CulturalRiddles: A Multicultural Benchmark of Riddles
As LLMs expand their language coverage, evaluating how well they understand and represent diverse cultures becomes increasingly important.
No.07Verdict: NotableScore█████░░░░░5.2 - arXivby Wang
TraceForge: Distilling with Your Own Thinking
Using an LLM to generate training data for another is among the most general ways to train one, and it remains common practice.
No.08Verdict: NotableScore█████░░░░░5.2
Briefs
- arXiv
Harness Scaling for Generalizable Agentic Reinforcement Learning
█████░░░░░5.1 - arXiv
Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?
█████░░░░░4.8 - arXiv
Think Harder Where It Matters: Item-Level Adaptive Recursion for Sequential Recommendation
█████░░░░░4.7 - arXiv
DiffResearch: Accelerating Deep Research with Diffusion Language Models
█████░░░░░4.5 - Hugging Face
VX-One: Typed, Calibrated Decision Heads for Real-Time Perimeter Triage - An empirical study of unknown-attack honesty, cascade gray zones, and calibration under drift
████░░░░░░4.3 - arXiv
StyleStream 2.0: Fast and Controllable Streaming Voice Style Conversion
████░░░░░░4.3 - arXiv
Multimodal Reranking Is a System One Decision
████░░░░░░4.2 - arXiv
ToM2Vec: Continuous Theory-of-Mind Tokens for Multi-Agent Coordination
████░░░░░░4.2 - arXiv
On the Limits of Scale: Inverse Scaling in Vision-Language Models
████░░░░░░4.2 - arXiv
F2G-Pose: Geometry-Aware Foundation Feature Lifting for Direct RGB-D Category-Level Object Pose Estimation
████░░░░░░4.2