arXiv
Verdict: NotableWeVisOne-VL: Unified Visual Perception from Objects to Pixels
Existing vision-language models (VLMs) remain unreliable for fine-grained visual perception.
- HF ▲ 239
- Stars ★ 107
Artificial Intelligence
Models, methods, and the machinery of intelligence.
Edition No. 27
Updated UTC
Top stories
1. DecisionPivot: A Diagnostic Benchmark for Decision Models in LLM Systems
Decision models support routing, guardrails, and output verification in LLM systems.
Verdict: Notable██████░░░░5.52. Retrieval Augmented Generation Compositionality
Retrieval Augmented Generation (RAG) grounds large language models in external knowledge.
Verdict: Notable█████░░░░░5.3
More top stories
- 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.03Verdict: NotableScore█████░░░░░5.2 - 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.04Verdict: NotableScore█████░░░░░5.1 - arXivby Bai, Song, Hao +5
Harness Scaling for Generalizable Agentic Reinforcement Learning
Agent harnesses have become a central component of modern agentic systems, shaping how models use tools, manage context, and coordinate long-horizon interaction.
No.05Verdict: NotableScore█████░░░░░5.0 - arXivby Cao, Tang, Zhou +2
Think Harder Where It Matters: Item-Level Adaptive Recursion for Sequential Recommendation
Existing sequential recommenders usually allocate a fixed computational budget to every item in a user's interaction history, regardless of the item's contribution to the final prediction.
No.06Verdict: NotableScore█████░░░░░4.8 - arXivby Zhong, Li, Carlini +1
Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?
Frontier coding agents are increasingly framed as end-to-end automated researchers, and ML for science offers a demanding test of that promise: improving a scientific model often requires ....
No.07Verdict: NotableScore█████░░░░░4.7 - arXivby Zhang, Lin, Hou +2
F2G-Pose: Geometry-Aware Foundation Feature Lifting for Direct RGB-D Category-Level Object Pose Estimation
This paper studies category-level RGB-D object pose estimation, which recovers an object's 3D rotation and translation without instance-specific CAD models or reference views.
No.08Verdict: NotableScore████░░░░░░4.4
Briefs
- arXiv
DiffResearch: Accelerating Deep Research with Diffusion Language Models
████░░░░░░4.4 - arXiv
StyleStream 2.0: Fast and Controllable Streaming Voice Style Conversion
████░░░░░░4.4 - 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
ToM2Vec: Continuous Theory-of-Mind Tokens for Multi-Agent Coordination
████░░░░░░4.2 - arXiv
Multimodal Reranking Is a System One Decision
████░░░░░░4.1 - arXiv
MoG-VLM: Efficient Video Anomaly Detection through Motion-Guided Vision-Language Models
████░░░░░░4.0 - arXiv
Parameter-Efficient Adaptation of Large Language Models to a Low-Resource Agglutinative Language: A Corpus, Datasets, and a Reproducible Benchmark for the Bashkir Language
████░░░░░░4.0 - arXiv
FrontierCS 2: A Benchmark for Computer Science R&D
████░░░░░░3.8 - arXiv
The Value of System 1 Models in Medicine
████░░░░░░3.8 - arXiv
Cost-Aware Abstention for LLM-Based IT Ticket Classification
████░░░░░░3.8