Multi-Aspect Runtime Verification for Simulation-Based V&V of LLM-Enabled Autonomous Agents
Research
Research News
New papers, breakthroughs and academic AI research
RoboJEPA: Scaling Robotic Latent World Models
Research
Constitution-Guided Watermarking
Research
Collaborative Reasoning Distillation via Cross-Feedback and Coherent Curation
Research
Trustworthy Domain-Specific AI for Structured Knowledge Retrieval and Reasoning
Research
Contextualization of Third-Party Cloud Security Findings
Research
DynStream: Online Streaming 4D Gaussian Reconstruction of Dynamic Worlds from Unposed Video
Research
Diffusion-Generated Image Watermarking: A Two-Axis Taxonomy and Three Protocol-Bounded Case Studies
Research
PatchBench: Measuring Collateral Damage in Activation Patching
Research
The Parser Already Knows: Lightweight Bias Correction in Constrained Decoding
Research
Dual-QK: Sharp Queries and Flat Keys for Prunable 2-bit KV Caches
Research
DSReg: Provably Recovering Individual World Latents without Reconstruction
Research