16 posts published in the last hour
- 02:32EXAM$^2$: $\underline{Ex}tending$ $\underline{A}udio$ $Understanding$ $in$ $\underline{M}ultilingual$ $and$ $\underline{M}ultimodal$ $Analysis$
- 02:32What Reaches Expert Review? Representation, Structural Screening, and Candidate-Form Dependence in AI-Assisted Item Development
- 02:32Intelligent transcription with Gemini 3.5 Transcribe
- 02:32Too much of a good thing — when knowledge distillation promotes overfitting, and how to avoid it
- 02:32Bringing ChatGPT for Teachers to more U.S. school districts
- 02:32Disentangled Skill Representations for Predictive Human Modeling
- 02:32Learning never stops: How AI makes learning continuous
- 02:32TrustShiftProbe: Characterizing, Benchmarking, and Defending Staged Trust Attacks on MCP Servers
- 02:03Beyond Executable Models: The Pufibara Agent Harness and the Modelica Agent Workflow Benchmark for Physical System Modeling
- 02:03The Limits of Automatic Evaluation of Creativity in Large Language Models
- 02:03How GoDaddy transformed its analytics with Amazon Quick
- 02:03Feedback That Backfires: Why Small Language Model Agents Repeat the Call They Just Watched Fail
- 02:02Natera’s intelligent appointment scheduling with Amazon Bedrock AgentCore
- 02:02ToolRobustBench: Stage-Wise Perturbation Evaluation and Failure Diagnosis for Tool-Calling Agents
- 02:02Preparing data for supervised fine-tuning Part 2: Advanced data strategies
- 02:02Confidently Wrong, Silently So: Auditing Undetectable Failures of a Deployed On-Device Language Model