arXiv
Verdict: NotableWeVisOne-VL: Unified Visual Perception from Objects to Pixels
Existing vision-language models (VLMs) remain unreliable for fine-grained visual perception.
- HF ▲ 241
- Stars ★ 143
Artificial Intelligence
Models, methods, and the machinery of intelligence.
Edition No. 28
Updated UTC
Top stories
1. Retrieval Augmented Generation Compositionality
Retrieval Augmented Generation (RAG) grounds large language models in external knowledge.
Verdict: Notable█████░░░░░5.22. CulturalRiddles: A Multicultural Benchmark of Riddles
As LLMs expand their language coverage, evaluating how well they understand and represent diverse cultures becomes increasingly important.
Verdict: Notable█████░░░░░5.0
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█████░░░░░5.0 - 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.04Verdict: NotableScore█████░░░░░4.9 - arXivby Avivi, Rahimi, Mendelson +1
Different Tasks, Different Timesteps: Temporal Task-Aware Quantization for Diffusion Language Models
Diffusion Language Models (DLMs) introduce unique quantization challenges due to their iterative denoising process.
No.05Verdict: NotableScore█████░░░░░4.7 - arXivby Gupta, Konan, Yin +2
AgentVQA: A Unified Benchmark for Agentic Visual Understanding
Vision-language models (VLMs) can perform a broad range of tasks across diverse settings, yet their performance in agentic contexts remains poorly understood.
No.06Verdict: NotableScore█████░░░░░4.7 - arXivby Liu, Ouyang, Lan +2
AnyGameRenderer: Entity-Consistent Generative Rendering Across Games and an Entity-Level Benchmark
AI coding agents can now build small playable games in minutes, but the results usually look like programmer art: gray blockouts, colored geometric primitives, and flat semantic blobs.
No.07Verdict: NotableScore█████░░░░░4.6 - 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
ToM2Vec: Continuous Theory-of-Mind Tokens for Multi-Agent Coordination
████░░░░░░4.1 - arXiv
Efficient Zero-Shot Video Anomaly Detection via Signal-Aware Adaptive Fusion (SAAF)
████░░░░░░3.9 - arXiv
SplatLab: Autonomous Scientific Discovery for 3DGS Research
████░░░░░░3.9 - arXiv
MoG-VLM: Efficient Video Anomaly Detection through Motion-Guided Vision-Language Models
████░░░░░░3.8 - 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
████░░░░░░3.8 - arXiv
Solvent: Long-Horizon Reasoning for Multi-Step Retrosynthesis
████░░░░░░3.8 - arXiv
FrontierCS 2: A Benchmark for Computer Science R&D
████░░░░░░3.7 - arXiv
Multimodal Generative AI Assists Comprehensive Echocardiographic Interpretation
████░░░░░░3.7 - arXiv
Green Code or Costly Code? Evaluating the Energy Costs of Iterative LLM-Based Code Optimizations
████░░░░░░3.7 - arXiv
MDMR-Bench: A Multi-Dimensional Benchmark for Multi-Reference Image Generation
████░░░░░░3.7