Knowledge catalogue
arXiv:2608.28666v1 Announce Type: new Abstract: Video-language models (VLMs) remain brittle on tasks that require tracking events over time and grounding answers in specific spatial regions. We propos
In an interview in this article for The @guardian about AI deception, I explain why misaligned behaviors emerge from reinforcement learning, why they will continue to pose risks as models become more
“increasing agent autonomy can gradually make human oversight ineffective by causing approval fatigue, overreliance, loss of situational awareness, and skill degradation.” new paper from @mmitchell_ai
arXiv:2608.29919v1 Announce Type: cross Abstract: The rapid proliferation of LLMs has further heightened the need to develop dependable AI-generated text detection, especially beyond English. Neverthe
arXiv:2608.29846v1 Announce Type: new Abstract: Sampled-token on-policy distillation (OPD) efficiently transfers capabilities from teacher to student using student-generated tokens, requiring teacher
arXiv:2608.29942v1 Announce Type: cross Abstract: The key limitation of current state-of-the-art influence-based guardrails is that they do not reliably distinguish a legitimate, user-authorized actio
arXiv:2608.29349v1 Announce Type: new Abstract: Gaussian process (GP) regression with a single global GP (GP-glo) incurs cubic computational cost, limiting scalability to large datasets. Product-of-ex
arXiv:2608.30561v1 Announce Type: cross Abstract: Informative label missingness can change the usual efficiency ordering between completely and partially labelled classifiers because the pattern of mi
arXiv:2608.30657v1 Announce Type: new Abstract: Fixed-viewpoint infrastructure sensors repeatedly observe the same traffic space, making roadside 3D occupancy structurally different from ego-vehicle p
arXiv:2602.19736v3 Announce Type: replace Abstract: Diffusion models now give the best perceptual quality in super-resolution (SR), but their architecture and training confine them to small fixed crop
arXiv:2607.16862v2 Announce Type: replace Abstract: LiDAR place recognition supports loop closure, relocalization, and multi-agent map management. As robotic platforms increasingly combine LiDARs with
arXiv:2608.30034v1 Announce Type: new Abstract: Two-stage vision pipelines often place an enhancement network before a task network, on the assumption that a cleaner input produces a better output. We
arXiv:2608.29783v1 Announce Type: new Abstract: Industrial anomaly detection is a critical component of modern manufacturing. Most traditional unsupervised methods rely on modelling normal feature dis
arXiv:2608.28696v1 Announce Type: new Abstract: Visual in-context learning (ICL) with multimodal large language models (MLLMs) is effective for fine-grained visual classification, but each retrieved i
arXiv:2608.29535v1 Announce Type: cross Abstract: Infectious disease transmission is shaped by patterns of human interaction, which adapt as epidemic conditions change. Capturing these context-depende
arXiv:2508.08966v2 Announce Type: replace Abstract: The attention mechanism lies at the core of the transformer architecture, providing an interpretable model-internal signal that has motivated a grow
arXiv:2608.28602v1 Announce Type: new Abstract: Parkinson disease PD is a progressive neurodegenerative disease that can have a significant impact on motor performance resulting in the appearance of s
arXiv:2608.28629v1 Announce Type: cross Abstract: Existing methods lack a generalized approach to efficiently identify and resolve the diversity of design defects in BIM. Therefore, this study propose
arXiv:2608.28762v1 Announce Type: new Abstract: Recent advances in visual question answering (VQA) and multimodal large language models (MLLMs) have enabled natural-language reasoning over traffic sce
arXiv:2604.02382v2 Announce Type: replace-cross Abstract: The scale and complexity of modern cloud infrastructure have made 'Infrastructure-as-Code' (IaC) essential for managing deployments through de
arXiv:2608.28612v1 Announce Type: new Abstract: Generating professional scholarly content, such as peer reviews and rebuttals, requires an intricate synergy between domain reasoning and factual ground
arXiv:2603.15034v2 Announce Type: replace-cross Abstract: This paper replicates and extends the system used in the AuTexTification shared task for authorship attribution of machine-generated texts. Ex
arXiv:2608.30025v1 Announce Type: new Abstract: Large language models (LLMs) frequently generate source code containing vulnerabilities, yet little work studies the internal mechanisms that distinguis
arXiv:2608.29901v1 Announce Type: cross Abstract: Electronic Health Record (EHR) prediction models in the intensive care unit must learn from sparse and irregular measurements while preserving the cli
Claude Fable 5.1 is now available on Amazon Bedrock and Claude Platform on AWS. This post covers Claude Fable 5.1's improvements, the Enterprise Frontier Safeguards for keeping your data in a cloud en
Introducing Fleet: GPU benchmarking entirely in your browser. Run WebGPU compute kernels drawn from real AI workloads directly on your hardware and earn a personalized card built for your device. Rate
Historically, enterprise predictive analytics tasks such as predicting churn, purchase intent, or fraud scoring have meant building custom models using libraries like XGBoost, Random Forest, or Deep N
arXiv:2602.06181v2 Announce Type: replace Abstract: Post-training quantization reduces the memory needed to run large language models but alters their social biases in ways that aggregate metrics fail
arXiv:2608.28705v1 Announce Type: cross Abstract: Dose accumulation is increasingly important in adaptive radiation therapy and reirradiation, but its clinical validity depends on the performance of d
arXiv:2608.29455v1 Announce Type: new Abstract: LLMs are increasingly used as human surrogates, often on the premise that richer persona data could make them substitutes or exploratory tools for speci
arXiv:2603.22978v2 Announce Type: replace Abstract: In the maintenance of complex systems, fault trees are used to locate problems and provide targeted solutions. To enable fault trees stored as image
arXiv:2608.28991v1 Announce Type: cross Abstract: Causal representation learning (CRL) aims to recover latent causal variables and their structural relations from high-dimensional observations. Existi
arXiv:2608.29892v1 Announce Type: new Abstract: Learning solution operators for partial differential equations (PDEs) on irregular and geometry-dependent domains remains a central challenge in scienti
arXiv:2608.29616v1 Announce Type: new Abstract: Criminal judgment prediction requires models to infer statutory articles, charges, and sentencing outcomes from case facts. Unlike standard classificati
arXiv:2608.29168v1 Announce Type: new Abstract: The LLM-as-a-Judge paradigm has emerged as a scalable alternative to human evaluation. However, single-model judges are limited by their inherent model
arXiv:2508.19485v2 Announce Type: replace Abstract: Gas leaks pose severe risks to human health and industrial safety. However, accurate and timely monitoring of gas leaks remains a major challenge. E
Kaitchup just posted results of his benchmarks for Qwen3.8 27B for quants from different labs, Q4 to Q1, . All the details are hidden behind the paywall, but high level result is visible and looks lik
arXiv:2512.16391v2 Announce Type: replace-cross Abstract: Attention is the dominant source of latency during long-context LLM inference, an increasingly popular workload with reasoning models and RAG.
arXiv:2608.30376v1 Announce Type: new Abstract: Recurrent, attention-free sequence models share a structural weakness: a fading state cannot perform exact recall of something seen once, far in the pas
arXiv:2503.19634v2 Announce Type: replace Abstract: Burst image super-resolution (BISR) reconstructs a high-resolution keyframe by aggregating complementary sub-pixel evidence from a short burst of lo
arXiv:2601.07794v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly evaluated on their ability to perform multi-hop reasoning, i.e., to combine multiple pieces of i
arXiv:2608.30316v1 Announce Type: new Abstract: Existing class-incremental learning methods struggle in multi-label scenarios (MLCIL) due to the inherent contradiction of learning objectives arising f
arXiv:2608.29472v1 Announce Type: cross Abstract: Knowledge distillation trains a small student model to reproduce the outputs of a large teacher model, and its progress is typically monitored through
arXiv:2608.30710v1 Announce Type: new Abstract: Historically originating from Hilbert's 13th problem, the Kolmogorov-Arnold representation theorem (KART) has recently experienced a major revitalisatio
South Korea announced a sovereign AI investment exceeding one trillion dollars, awarding most of the contracts to Nvidia while sidelining competitors such as Hynix due to policy alignment criteria. Th
arXiv:2505.22255v4 Announce Type: replace-cross Abstract: Sparse Autoencoders (SAEs) decompose language-model activations into sparse, interpretable features, but standard encoders usually treat the l
arXiv:2512.17452v4 Announce Type: replace-cross Abstract: Long-context LLM inference is bottlenecked by the quadratic attention complexity and linear Key-Value (KV) cache growth. Prior approaches miti
arXiv:2608.30216v1 Announce Type: cross Abstract: Topic models are widely used for content analysis, where users often analyze corpora around predefined labels rather than unordered latent topics. Exi
arXiv:2601.06631v2 Announce Type: replace Abstract: Building NLP systems for subjective tasks requires one to ensure their alignment to contrasting human values. We propose the MultiCalibrated Subject
arXiv:2608.30226v1 Announce Type: new Abstract: Modular compression has enabled considerable parameter reduction in LLMs while preserving strong language understanding and downstream task accuracy. Ho
arXiv:2508.15757v2 Announce Type: replace Abstract: Configuration optimization remains a critical bottleneck in machine learning, requiring coordinated tuning across model architecture, training strat
arXiv:2608.31009v1 Announce Type: new Abstract: Structure-based drug design (SBDD) requires ligands that satisfy both 3D target affinity and 1D chemical validity. Existing controllable generation meth
arXiv:2608.30583v1 Announce Type: new Abstract: Standard language proficiency tests rely on linguistic tasks such as vocabulary, grammar and reading comprehension quizzes. An alternative, cognitively
arXiv:2608.31037v1 Announce Type: new Abstract: Neural audio codecs (NACs) convert speech into discrete token sequences, and prior work has reported that these sequences follow language-like statistic
arXiv:2608.29767v1 Announce Type: new Abstract: Discrete trajectory checks can miss collisions between sampled robot states. Reachability-based certification bounds motion between states, but uniform
arXiv:2505.15741v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) and Evolutionary Computation (EC) are increasingly being combined to support automated optimization, algorithm de
arXiv:2608.29257v1 Announce Type: new Abstract: Multiple-choice questions (MCQs) are a standard format for evaluating large language models (LLMs), yet the popularity of answer options can confound ev
arXiv:2505.16305v3 Announce Type: replace Abstract: While CANDECOMP/PARAFAC (CP) decomposition (CPD) is fundamental for tensor reconstruction, Bayesian CPD often scales poorly because variational upda
arXiv:2508.13073v3 Announce Type: replace-cross Abstract: Robotic manipulation, a key frontier in robotics and embodied AI, requires precise motor control and multimodal understanding, yet traditional
arXiv:2608.29685v1 Announce Type: new Abstract: Early failure prediction is important for long-horizon agents, as it enables timely intervention and can reduce inference and tool-use costs. Uncertaint