Signal over volume.

AI Adoption Linked to Higher Scientific Creativity via Distinct Research Path...

AI Adoption Linked to Higher Scientific Creativity via Distinct Research Pathways

Active Exploration Resolves Adult 'Conjunctive Handicap' in Causal Reasoning

Rethinking Continual Experience Internalization for Self-Evolving LLM Agents

SuperMemory-VQA: A New Benchmark for Long-Horizon Egocentric AI Memory Assist...

SpatialAct: Bridging the Reasoning-to-Action Gap in 3D VLM Agents

PlatonicNav: Unifying Robot Navigation via Shared Semantic Manifolds

Imaginative Perception Tokens: Teaching VLMs to Mentally Simulate Unseen Spat...

RoboStressBench: A Principled Framework for Evaluating VLM Robustness to Phys...

AFUN: A Foundation Model for Predicting Where and How to Interact with Objects

TVRBench: Bridging the Gap in Active Spatial Intelligence for Foundation Models

Beyond Correctness: Auditing Source-Dependence in Multi-Source Medical RAG Sy...

τ0-WM: A Unified Video-Action World Model for Robust Robotic Manipulation

PaSBench-Video: Exposing the Failure of MLLMs in Proactive Safety Warning

HLL Benchmark: Testing if Multimodal Agents Can Cross Humanity's Last Line of...

Beyond One-Shot: Tool-Augmented AI Agents Transform Experimental Data into Cu...

Verifiable Belief-Space Safety Filters: Reducing Conservativeness in Interact...

SwanBench-Speech: A New Multi-Dimensional Benchmark for Long-Form Speech Gene...

FLAT-PACK BENCH: Exposing the Spatio-Temporal Reasoning Gaps in Large Vision-...

BenHalluEval: A New Multi-Task Hallucination Benchmark for Bengali LLMs

Unlocking Concept Binding: Why CLIP Fails and How Transformers Can Succeed

GE-Sim 2.0: Closing the Loop with a High-Fidelity Video World Simulator for R...