Privacy and Identity
What's New
- CryoAtlas: A Large Curated Dataset and Unified Benchmark for Cryo-EM Atomic Model Building
- AgentOrch: How Close Can Global Orchestration Come to Step-by-Step Interaction?
- Show HN: Compile the same source for GPUs and CPUs
- Lineage Is Memory: Parent Inheritance and Feedback Disclosure in Short-Budget LLM-Guided…
- Radial Kernel Attention for Long-Range Modeling in Polymer Machine Learning Force Fields
- Cloud Security Summit - BrightTALK Summits
- I3L: Iterative Interactive Imitation Learning for Whole-Body Mobile Manipulation
- Everyone’s a Builder Now: How to Govern Vibe Coding, MCP, and AI Agents at Scale
- DiTGaze: Geometry-Conditioned Diffusion Augmentation for Few-Shot Gaze Estimation
- Microsoft named a Leader in the 2026 Gartner® Magic Quadrant™ for SIEM
- Introducing harness adapters: adapt your favorite model to your harness to improve performance and…
- nginx2root: Five new nginx vulnerabilities, and how Cloudflare protects origins from the worst of…
- Toward a Science of AI Agent Societies
- When AI Analysts Disagree: Agentic Multiverse Analysis and the Robustness of Empirical Research
- Ask in the Crowd: Differentially Private LLM Inference via Dummy-Augmented Shuffling
- Living off the Local Model: Abusing Browser-Embedded Language Models for Post-Exploitation
- MAWAM: A Multi-Agent World-Action Model for Coordinated Manipulation
- DSFlow: A Neuro-Symbolic Data Workflow Agent with Statistical Diagnostic Guardrails
- When Objectives and Evaluators Disagree: Evaluating Transfer for Post-hoc Demographic Framing…
- Gravitational Duals from Equations of State II: Large Hierarchies and False Vacua
- Awaken-HI: Scaling Humanoid Intelligence with Whole-Body Human Experience
- How Large Language Models Misrepresent American Climate Opinions
- Agent^2 RL-Bench: Can LLM Agents Engineer Agentic RL Post-Training?
- HabitusMem: Belief Memory over Evolving User Preferences for LLM Agents
- What If Chain-of-Thought Is Not Enough?
- Actor-Predictor Architecture for Reinforcement Learning with Formal Specification Objectives
- Anchor and Check: Deterministic Cross-Prompt, Cross-Model Reconciliation for Auditable LLM Decisions
- SoK: Assessing the Evolution of LLM Capability in Software Vulnerability Research
- Closing the Analyze-to-Design Gap: An Authorization-Bounded Agent for Self-Driving Laboratories
- SPARK: Adaptive Parametric Knowledge Participation for Faithful Retrieval-Augmented Generation
- Raptor: Rejection-aware Adaptive Tree based on Speculative Decoding
- How to "train" a surgeon? Benchmarking generalist agents in surgical scene understanding
- The FrontierOR Challenge: Agentic Algorithm Design for Operations Research
- From Cases to Criteria: Reusing Evaluation Knowledge for Task-Specific Rubric Generation
- AppSci-Bench: Can LLMs Build AI Agents and Make Them Better?
- MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems
- Online Temporal Rotations for 2 Bit KV-Cache Quantization in Video Diffusion Transformers
- Beyond Weight Updates: Evolving Agent Harnesses for Domain Specialization
- VisAlloc: Allocating Visual Supervision for On-Policy Self-Distillation
- Tokengeist: Multi-Turn Attribution Tracing in Agentic Conversations

