ANCHOR: Cluster-Grounded 5W1H Extraction via Large-Small Model Collaboration
Deep semantic understanding of events requires recognizing related events and distinguishing why an event occurs from how it is carried out. 5W1H extraction provides a structured foundation for such understanding by organizing event inform...
2026-11-16Researchresearchmodel
Can AI Mature a Model's Geometry? Training-Free Weight Baking in LLMs
Can an AI make a trained language model more mature, in the sense of a better organized latent space, by looking only at the geometry of that space? An analyst model reads a fixed-size digest of topological descriptors of the layers of a f...
2026-11-16Researchresearchlanguagellm
Can LLMs Give Good Product Advice? A Framework for Diagnosing Failures
Evaluating product advice from a language model requires assessing whether the recommendation meets the user's needs and identifying where the model falls short when it does not. However, matching a product mentioned in an online reply can...
2026-11-16Researchresearchevallanguage
Compressed Simulation-Based Inference: Neural Posterior Estimation for Massive Data via Low-Dimensional Sketches
Neural posterior estimation (NPE) is a popular Bayesian simulation-based inference (SBI) approach that uses neural networks trained on simulated data--parameter pairs to approximate the posterior given a user-chosen prior. For high-dimensi...
2026-11-16Researchresearchinferenceneural
Deep Learning for Physicists: From Linear Regression to Reasoning Models
These lecture notes are based on an introductory course on neural networks and deep learning that the author taught in the School of Mathematical Sciences at Queen Mary University of London in 2023/24 and 2024/25. The author, however, is a...
2026-11-16Researchresearchmodelneural
Fast at the Frontier, Wrong at the Fallback: A Commit-Level Analysis of Threshold Decoding in Diffusion Language Models
Diffusion language models (DLMs) can write several tokens per forward pass. Open-weight DLMs commit, in any order, every masked position whose confidence passes a threshold. If none does, a fallback commits the most confident one, and the...
2026-11-16Researchresearchlanguagemodel
GPRM: Global Perspective Process Reward Model
Process Reward Models (PRMs) are widely used for step-level evaluation of multi-step reasoning in large language models, but existing methods are often limited by weak historical dependency modeling and insufficient global awareness. They...
2026-11-16Researchresearchevallanguage
High-probability Uniform Mixing via Dobrushin Contraction and Accelerated Hamiltonian Monte Carlo
Hamiltonian Monte Carlo, since its invention and subsequent rise to widespread use, has been motivated by its ability to accelerate convergence to equilibrium compared to diffusive methods, both in terms of dependence on condition number a...
2026-11-16Researchresearch
IndustrialKnowEval: A Benchmark for Evaluating Multi-Level Industrial Knowledge in LLMs
Large language models (LLMs) are increasingly explored for industrial tasks, yet few benchmarks evaluate their mastery of industrial knowledge across different types of cognitive demand. We introduce IndustrialKnowEval (IndKnow), a benchma...
2026-11-16Researchresearchbenchmarkeval
Instant Weight-Space Consolidation for Long-Term Memory in LLMs
Agentic memory systems give LLMs persistent memory by extracting experience into text and retrieving it at query time, but the model itself does not evolve: however many interactions it has had, it starts each query the same. Extraction er...
2026-11-16Researchresearchagentllm
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
MemEmo: Evaluating Emotion in Memory Systems
Memory systems address the challenge of context loss in Large Language Models during prolonged interactions. However, as an essential tool for warm companionship and personalized services, the effectiveness of memory systems in processing...
2026-11-16Researchresearchevallanguage
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
Programmable Semantic Interventions: Learning Causal Carriers from Behavioral Programs
Causal abstraction explains a frozen network by aligning its activations with the variables of a simpler, interpretable model, and checking that interventions on the two agree. Finding such an alignment currently requires a counterfactual...
2026-11-16Researchresearchmodel
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
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
Wavelet-Energy-Driven Dynamic Patching for Time Series Forecasting
Patch-based transformers tokenise a time series into fixed-size, uniform windows, which commits the model to a single temporal resolution even though real signals are multi-scale. The discrete wavelet transform (DWT) is a natural alternati...
2026-11-16Researchresearchmodeltransformer
When the Bill Falls: Reusing the Old Index Defers,Never Avoids, Re-encoding in Complete Embedding-Model Migration
Upgrading the embedding model behind a vector index requires re-encoding the corpus. Recent work reuses the old index through adapters or window re-ranking. Across sixteen model pairs on passage and code corpora, plus eleven on Natural Que...
2026-11-16Researchresearchmodel
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