Knowledge catalogue
arXiv:2610.06511v1 Announce Type: new Abstract: To evaluate the frontier, we must measure models not by what they say, but by what they can engineer and build in grounded physical environments. We int
arXiv:2610.06851v1 Announce Type: new Abstract: In this paper, we study how training data creates associations between the tokens at the start of a base model's response and the reasoning behavior tha
arXiv:2610.06439v1 Announce Type: new Abstract: What happens when a legal AI model learns to look like a lawyer instead of reasoning like one? We fine tune Qwen3-8B with Group Relative Policy Optimisa
arXiv:2610.05483v1 Announce Type: new Abstract: World--action models (WAMs) promise a unified model that predicts action-conditioned futures, generates feasible actions, and supports planning in imagi
arXiv:2610.04721v1 Announce Type: new Abstract: Structural diagrams are widely used to represent complex systems and relational information across scientific, engineering, procedural, and spatial doma
arXiv:2606.14222v2 Announce Type: replace Abstract: The rapid evolution of Time Series Foundation Models (TSFMs) has advanced zero-shot forecasting across diverse domains. Inspired by the current form
arXiv:2610.04502v1 Announce Type: new Abstract: Medical Vision-Language Models (Med-VLMs) have demonstrated strong capabilities in clinical tasks. However, they often struggle to understand anatomical
arXiv:2610.05265v1 Announce Type: new Abstract: Looped language models provide a parameter-efficient way to scale iterative test-time computation by repeatedly executing a shared recurrent core. Post-
arXiv:2610.05458v1 Announce Type: new Abstract: Running the same language model on different graphics processing unit (GPU) vendors can produce different logits, even when the model weights and inputs
arXiv:2610.05277v1 Announce Type: cross Abstract: Code language models must be maintained like the software around them: when a library evolves, a model keeps writing the interface that it saw during
Looped language models repeatedly apply a weight-shared block to increase effective depth without increasing parameter count, but the resulting T sequential recurrent-block calls per generated token s
arXiv:2610.05699v1 Announce Type: new Abstract: The efficacy of traditional disease prediction is limited by spatial gaps and temporal lags, which impact the timing and targets of resource deployments
arXiv:2610.04920v1 Announce Type: new Abstract: Pretrained world models can generate diverse environments, yet users often want to explore a particular scene specified by their own video. This require
arXiv:2610.06598v1 Announce Type: cross Abstract: Action-conditioned robot world models must respond precisely to robot trajectories while preserving realistic visual dynamics, yet learning both from
arXiv:2610.05000v1 Announce Type: new Abstract: Concept erasure is essential for the safe deployment of text-to-image diffusion models, as they may reproduce harmful, copyrighted, or privacy-sensitive
We are releasing the only Western OSS LLM that is competitive with the best Chinese OSS models for coding tasks! Mistral Large 4 preview, AKA le Chonk 🐈 is SOTA OSS on cyber and human evals. Check 🧵 b
arXiv:2610.04128v1 Announce Type: cross Abstract: Split learning lets a client train a language model on a server without sending its text. The client runs the first layers itself and sends the server
arXiv:2610.02659v1 Announce Type: cross Abstract: Modern state space models (SSMs), such as Mamba2, provide a compelling alternative to transformers by combining linear-time sequence modeling with rec
arXiv:2610.02593v1 Announce Type: new Abstract: Data selection is already a central bottleneck in large-language-model training, where web-scale corpora are noisy and token budgets are finite. In cont
arXiv:2610.02967v1 Announce Type: cross Abstract: Recent text-to-image generation models have achieved remarkable visual quality, but improving them through post-training remains challenging because n
arXiv:2508.13408v3 Announce Type: replace Abstract: Chemical Language Models (CLMs) are increasingly used in de novo drug design, driven by recent growth in model scale, compute, and dataset size. How
arXiv:2610.01395v1 Announce Type: new Abstract: Muon improves large-scale training by applying a spectral-norm steepest-descent update to matrix parameters, but practical models also contain parameter
arXiv:2610.00706v1 Announce Type: cross Abstract: Large audio-language models (LALMs) are sensitive to input perturbations, such as noise, waveform corruption, and adversarial injections. We propose A
arXiv:2610.01625v1 Announce Type: new Abstract: Federated parameter-efficient fine-tuning enables distributed clients to adapt pretrained vision-language models without sharing raw data or updating th
Decision models in llama.cpp are now available The `/v1/systemone` endpoint is available in the latest llama builds. Use it to do Jev-style inference locally, efficiently and privately. Multiple open
arXiv:2610.01019v1 Announce Type: new Abstract: Robotic world models predict action-conditioned future scenes, providing a foundation for understanding action outcomes. However, turning alternative pr
arXiv:2610.00677v1 Announce Type: new Abstract: Advancements in augmented reality (AR) continue to foster innovative solutions, facilitating novel methodologies within educational systems, healthcare
arXiv:2610.00399v1 Announce Type: new Abstract: Metacognition involves reasoning about cognitive processes themselves. An example is in resource allocation where we choose how much time and effort to
one of the most challenging tasks for frontier models is being able to extract thousands of values from extremely dense tables in documents. our new Extract v2.5 agents are able to get 93%-96%+ on lon
arXiv:2610.01614v1 Announce Type: new Abstract: Generative video world models can now synthesize open-ended environments that agents can navigate and interact with in simple ways. Yet open-ended gener
arXiv:2610.01162v1 Announce Type: new Abstract: Reliable video world models could provide scalable predictive environments for robot learning, planning, and evaluation. However, generated robot videos
arXiv:2610.02191v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated striking capabilities on frontier mathematical problems, it remains unclear whether they possess th
arXiv:2610.00895v1 Announce Type: cross Abstract: Foundation models remain vulnerable to spurious correlations and ``Clever Hans'' strategies. Explainable machine learning can find and remove such str
arXiv:2610.00835v1 Announce Type: new Abstract: Text-to-music generation models are trained on massive music collections, creating a growing need for data attribution methods that can quantify the con
arXiv:2511.00763v3 Announce Type: replace Abstract: We investigate the performance of large language models (LLMs) on repetitive deterministic prediction tasks and study how the sequence accuracy rate
arXiv:2609.39277v1 Announce Type: cross Abstract: Looped models reason by applying the same block of weights many times, so compressing that block saves memory traffic on every loop. Compressed looped
arXiv:2609.40290v1 Announce Type: cross Abstract: In algorithmic statistics a string x is explained by a finite set containing it, and Kolmogorov's structure function records the smallest such model a
Brandon Vigliarolo / The Register: Cloudflare debuts open-weight multimodal decision models Clef and Clef-flash, claiming they are smarter and faster than Jev, based on Qwen3.8-27B and Qwen3.5-9B — Su
arXiv:2609.38385v1 Announce Type: new Abstract: Supervised fine-tuning of discrete diffusion language models masks some response tokens and trains the model to recover their original values from the v
arXiv:2510.17932v5 Announce Type: replace-cross Abstract: We introduce Chart2Code, a new benchmark for evaluating the chart understanding and code generation capabilities of large multimodal models (L
arXiv:2511.22232v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) are increasingly capable in medical imaging, yet most focus on single-image settings. Clinical interp
arXiv:2509.03122v5 Announce Type: replace-cross Abstract: Reliable model fingerprints are essential for protecting large language models (LLMs) against unauthorized redistribution and commercial misus
arXiv:2609.39492v1 Announce Type: new Abstract: Matching the same vehicle across front and rear cameras is difficult because the cameras do not share a view and the vehicle's appearance changes substa
arXiv:2609.39692v1 Announce Type: cross Abstract: On-policy distillation (OPD) has demonstrated two important capabilities in language models: compressing large teachers into smaller students and merg
arXiv:2609.38257v1 Announce Type: cross Abstract: Code editing requires a model to decide where to make changes, generate the new content, and preserve everything else. We study how masked diffusion l
arXiv:2609.38298v1 Announce Type: new Abstract: Vision Language Models (VLMs) are widely deployed in safety-critical scenarios, and understanding to which extent they can be controlled by adversarial
arXiv:2609.38181v1 Announce Type: new Abstract: Survival analysis estimates time-to-event outcomes from patient covariates and is widely used for medical risk assessment. Patients seeking prognostic i
arXiv:2609.39820v1 Announce Type: cross Abstract: Vision-language-action (VLA) models generalize broadly across robotic manipulation tasks, but complex environments require balancing task success with
arXiv:2609.38827v1 Announce Type: new Abstract: Direct-decision models turn text into low-latency structured labels and scores, making them attractive for classification and automatic evaluation. Yet
arXiv:2609.39024v1 Announce Type: new Abstract: Text-to-image (T2I) generation is gaining increasing popularity with the general public, motivating the development of reliable mechanisms for copyright
arXiv:2609.39551v1 Announce Type: new Abstract: Auto-research agents, LLM systems that propose, implement, train, and evaluate model changes across iterations, promise to automate applied ML's experim
arXiv:2609.39386v1 Announce Type: new Abstract: Pretrained time-series foundation models (TSFMs) are evaluated as forecasters of future values, yet for sparse series many decisions depend only on whic
arXiv:2609.36368v1 Announce Type: cross Abstract: Large foundation models have been introduced with the promise of efficient adaptation to downstream tasks. Yet, under limited supervision, MLLMs, an i
arXiv:2609.36492v1 Announce Type: cross Abstract: We benchmarked vision-language models (VLMs) on the decisions annotators take when inspecting electron microscopy images in connectomics: synapse dete
arXiv:2609.37725v1 Announce Type: new Abstract: We introduce Context Language Models (CLMs), language models that natively manage their own context. We implement this by treating the context as a file
arXiv:2603.08064v3 Announce Type: replace Abstract: Most evaluations of generative models rely on feature-distribution metrics such as FID, which operate on continuous recognition features that are ex
arXiv:2609.35804v1 Announce Type: cross Abstract: Large language models (LLMs) have shown remarkable capabilities in various natural language processing tasks, leading to their widespread deployment a
arXiv:2609.36860v1 Announce Type: new Abstract: We present IronLLM-0.6B, a 654M-parameter language model designed for efficient on-device inference. IronLLM-0.6B combines a hybrid attention architectu
arXiv:2609.35779v1 Announce Type: cross Abstract: Given recent achievements of large language models (LLMs), frontier models are expected to perform well on Bayesian reasoning tasks, at least as well
Last Week in AI #345 notes that Anthropic and OpenAI are in a close race to launch more capable but cheaper models this month: Anthropic unveiled Claude Opus 5.5 with stricter cybersecurity safeguards