14 posts published in the last hour
- 05:32Text, Pixels, or Both? Evaluating Input Representations for Multimodal Document QA
- 05:32Generative Embodied Multiple Behavior Control Systems for Human-like Agents
- 05:32Toward Auditable and Calibrated AI for Dementia-Related Crash Severity Prediction: A Selective Deferral Framework to Support Human Review
- 05:32OpenAI Releases GPT-6 Sol and Luna: 50% Cheaper API Pricing and Benchmarks
- 05:32Self-Organizing Agent Teams Learn to Reason Together
- 05:32‘We’re already fighting yesterday’s battle’: Greece’s prime minister gets candid about AI
- 05:32A Survey on the Linear Representation Hypothesis
- 05:03AutoGym: Blueprint-First Generation of Verifiable Agent Gyms
- 05:03Splitting Documents at Lower Cost: Multi-Split Boundary Decisions for LLM-Based Page Stream Segmentation
- 05:03GaitVista: Reliability-Aware AI Measurement toward Accessible Longitudinal Gait Assessment
- 05:03SpeakON Ships a MagSafe AI Voice Button With Its Own Microphone
- 05:03EvidenT: Building Trustworthy Enterprise Assistants through Evidence Groundedness and Traceability
- 05:03“We’re already fighting yesterday’s battle”: Greece’s prime minister gets candid about AI
- 05:03MAWILE: Multi-Axis Workbench for Inspecting LLM Evaluators