Pressure, Context, and Machine Self-Control: A Criminological Test of Reward Hacking in Generative AI Models
Research
Research News
New papers, breakthroughs and academic AI research
InstMoE: Adaptive Multimodal Routing with Specialized Experts
Research
Verification Trap: Understanding Test-Time Selection Failures under False Premises in Code Generation
Research
COMPASS: Comet Object Measurement Pipeline with Automated Selection and Scoring
Research
Decouple, Purify and Unite: Semantic-Structural Prototype Learning for Federated Medical Segmentation
Research
Dynamic Routing as a New Dimension for Test-time Versatility of LLMs
Research
Agent Behavior as Code: Efficient and Robust LLM Agents with Programmatic Specifications
Research
GitSwarm: Decentralized Compounding Inference
Research
SpecFold: Folding Multi-Branch Redundancy for Faster Speculative Decoding in Diffusion Language Models
Research
BARQ: Balanced Codebook Refinement for Low-Bit LLM Quantization
Research
UnAct: Gradient-Free Unlearning via Targeted Activation Intervention
Research
Formalizing the Moral Evaluation of Speech Acts: Truthfulness, Lies and Ethical Dilemmas
Research