Verifiable Rewards Improve Native Visual Reasoning Training
A 300-task procedural suite replaces preference-only judging with task-specific scorers, raising matched reinforcement-learning performance from 0.509 to 0.548.
Sep 4, 20264 min2608.26105
Artificial Intelligence
cs.AICovers all areas of AI except Vision, Robotics, Machine Learning, Multiagent Systems, and NLP.
Sort:
Million-Clip Dataset Tests Video Reasoning Beyond Visual Quality
VBVR pairs 200 curated reasoning tasks with rule-based, human-aligned evaluation to study whether video models generalize across spatiotemporal reasoning problems.
Aug 30, 20264 min2602.20159
Mobius Separates Knowledge From Reasoning for Faster Inference
A shared feed-forward memory and iterative attention reasoners retain comparable downstream scores while reducing continual-pretrained 35B-model inference time by nearly 4×.
Aug 25, 20264 min2608.14290
SkillNet Cuts Agent Steps Through Reusable Skills
An ontology, evaluation scheme, and 600,000-skill repository let agents retrieve and compose prior procedures, reporting 40% higher rewards with 30% fewer steps.
Aug 23, 20264 min2603.04448
Agent Swarm Cuts Complex Task Latency Up To 4.5×
Kimi K2.5 couples joint text-vision training with dynamically scheduled parallel subagents, improving agentic search scores while reducing time to target quality.
Aug 13, 20264 min2602.02276
Monocular Navigation Surpasses Depth-Based Systems on R2R-CE
An 8B vision-language model predicts image-space waypoints from a single RGB stream, reaching 77.4% unseen-environment success while cutting supervised training tokens 22×.
Aug 5, 20264 min2607.20785
FilmBench Reveals Cinematic Gaps in Video Generators
A director-designed taxonomy and evaluation agent track human model rankings at Spearman ρ=0.95–0.96 while exposing multi-shot and dynamic-aesthetics failures.
Aug 3, 20264 min2607.24241
Request-Level Sharing Cuts Recommendation Inference Cost
ROCS separates request-side and candidate-side computation, reaching up to 3× higher retrieval QPS and 50% higher ranking QPS in production.
Aug 1, 20265 min2607.27744
Mini Activations Narrow Frontier Model Gaps
A sparse 229.9B-parameter MoE activates 9.8B parameters per token and pairs agent-native data with RL for coding, cowork, and reasoning tasks.
Jul 31, 20265 min2605.26494
Open Image Model Narrows Gap Under Tight Compute
Boogu-Image-0.1 combines a stronger multimodal encoder, agentic prompt rewriting, and curated data to train competitive generation and editing models for about $400K.
Jul 29, 20265 min2607.13125 Code available