Beyond Job Titles: Interpreting Early-Career Job Advertisements with Sparse Autoencoders and Semantic Clustering
Job titles and job descriptions alone provide limited insight into how technical roles differ in a changing job market. To assess how such roles differ in their work and industry applications, we design and compare two methods based on dee...
2026-11-16Researchresearch
How VLMs Plan What's Next
When a vision-language model describes an image, it names one object at a time and it rarely repeats itself, yet how the model plans this order is far from obvious. We characterize the mechanism a VLM uses to decide where to look before it...
2026-11-16Researchresearchlanguagemodel
Hyperlyve: Parallelized Enumeration and Exact Lyapunov Stability Certification for Deep ReLU Networks
We introduce Hyperlyve (Hyperplane Partitioned Lyapunov Verification and Enumeration), a framework for proving the asymptotic stability of nonlinear dynamical systems, including those with neural network controllers. Hyperlyve learns and f...
2026-11-16Researchresearchneural
Latent Lattice Language Models
Language models typically increase per-token computation through deeper or looped layers and latent reasoning steps, while richer residual connections improve information flow across layers. We instead increase computational capacity: the...
2026-11-16Researchresearchlanguagemodel
Mitigating Catastrophic Forgetting with Physics-Indexed Specialist Memory: the Evolutionary Neuroplastic Agent
Continual reinforcement learning requires adaptation to changing conditions while preserving performance under previously encountered dynamics. It was investigated whether specialists generated by evolutionary search can provide a reusable...
2026-11-16Researchresearchagent
Optimistic Verifiers Get Hacked: Reward Hacking Under an Exact Process Oracle
Reinforcement learning from verifiable rewards inherits whatever its verifier gets wrong. Outside mathematics and code the verifier is a proxy, a rubric, a learned judge or a hand-written checker, and its distance from the true objective i...
2026-11-16Researchresearch
Reading or Remembering? Measuring Temporal Contamination in Language Models
Language models are now used to read central-bank text for economic forecasting, but most were trained on text written after the documents they read. A model reading a 2021 FOMC statement may already know that inflation rose in 2022, so pa...
2026-11-16Researchresearchlanguagemodel
Right Reason, Wrong Advice: Evaluating Recourse in LLM Explanations of Denied Requests
Language models increasingly write the explanations people receive when a rule system denies their request. If several rules deny the request independently, an explanation can name a true reason and still leave the person denied after they...
2026-11-16Researchresearchevallanguage
ScenarioForge: Resource-Grounded Generation and Execution Validation of Cyber Exercises
Cyber-range and capture-the-flag scenario construction remains labor-intensive because authors must coordinate infrastructure, vulnerable services, attack paths, artifacts, and success conditions. LLMs can propose detailed exercises, but p...
2026-11-16Researchresearchllm
Seen but Unsaid: Locating and Repairing Cross-Image Comparison in Vision-Language Models
Vision-language models (VLMs) often fail to match a point or an object across two images, even when the answer can be decoded from their own hidden states. We trace this failure from the visual tokens to the answer letter, in Qwen3-VL (2B-...
2026-11-16Researchresearchlanguagemodel
Severe but Harmless: Stress-Testing Shift Severity for Frozen Time-Series Forecasters
Zero-shot time-series foundation models (TSFMs) have become attractive alternatives to task-specific models because they handle diverse downstream tasks, including anomaly detection and forecasting, without per-series training. However, ti...
2026-11-16Researchresearchfoundationmodel
TRACE: Topological Representations for Anomaly detection through Contrastive Embeddings
Intrusion detectors must recognize evolving malicious behavior even when confirmed attack labels are scarce or incomplete. We present TRACE, a topology-aware graph contrastive learning framework for label-efficient intrusion detection. TRA...
2026-11-16Researchresearch
ViRA: Toward Ultra-High-Resolution Visual Agents via Cross-Input Relative Policy Optimization
Visual agents answer questions about ultra-high-resolution photos by zooming into the relevant regions. However, existing agents often answer from common sense instead of reading the evidence. Reinforcement learning (RL) on the final answe...
2026-11-16Researchresearchagent
When Tool Names Are Not Identities: Measuring Provider Misbinding in MCP-Based AI Agents
Large language model (LLM) applications increasingly act as agents that select and invoke external tools. The Model Context Protocol (MCP) standardizes this interaction by allowing clients to compose tools advertised by multiple servers. H...
2026-11-16Researchresearchagentlanguage
Agile Deliberation: How AI helps humans define the gray areas
Data Mining & Modeling
2026-11-04Officialresearchofficialmodel
The sleep framework: A new way for LLMs to retain knowledge in continual learning
Education Innovation
2026-10-27Officialresearchofficialllm
Bringing foundational models to the front lines of TB screening
Generative AI
2026-10-23Officialresearchofficialgenerative
Empowering frontline maternal care with AI-assisted ultrasound
Health & Bioscience
2026-10-21Officialresearchofficial
Grounding AI agents in biological reality: Building blocks for autonomous wet labs
General Science
2026-10-16Officialresearchofficialagent
Putting Earth AI to work: Geospatial agents for our planet's biggest challenges
Earth AI
2026-10-14Officialresearchofficialagent
Unlocking Earth AI’s planetary geospatial foundation models for global public health
Earth AI
2026-10-06Officialresearchofficialfoundation
Open and Emergent Problems in Agentic Privacy and Security: A Contextual Angle
Generative AI
2026-10-05Officialresearchofficialagent