15 posts published in the last hour
- 11:34What Survives When Activation Steering Is Used as Memory
- 11:34VC-OPD: Visual Counterfactual On-Policy Distillation for Grounded Vision-Language Reasoning
- 11:34Meta joins enterprise agent race with Muse Wonder, facing a trust gap
- 11:34MCPDisCo: Seesaw-Mitigated Tuning for MCP-Native Agents
- 11:34Customs Compliance Is Becoming an AI Problem
- 11:34AlphaRLM: Aligning Language Models for Literature-Grounded Symbolic Factor Discovery
- 11:34Mueon Raises $65M Series A to Move Cubelets Toward Production Readiness
- 11:34Predicting how model propensities generalize out of distribution
- 11:05WorkBorne: Discovering Agentic Tasks from Real-World Artifact Transitions
- 11:05Bridging Risk Approximation Gaps in Model Predictive Task Sampling via In-Context Modeling
- 11:05MARL-BattleGrounds: A Novel JAX-native Benchmark for Heterogeneous and Competitive Multi-agent RL
- 11:055 AutoHotkey Scripts for Data Scientists
- 11:05SkillForgeBench: Evaluating Agent Reliability Grounded in Agent Skill Specifications
- 11:05Your secrets aren’t safe with this cute robot toy — they’re on Chinese servers ready to be hacked
- 11:05Probable but Not Valid: A Psychometric Audit of Decision Models as Synthetic Survey Respondents