Knowledge catalogue
I recently started using local LLM for mostly coding tasks for my personal projects. I also have found local models responding much better for topics such as health, fitness, ergonomics etc. compared
arXiv:2610.11362v1 Announce Type: cross Abstract: Binary diffusion models typically require a large number of function evaluations (NFEs) to generate high-quality samples, making practical inference c
arXiv:2610.12235v1 Announce Type: new Abstract: AI research agents automate the cycle of proposing, implementing, and evaluating experiments, opening a path toward recursive self-improvement. Yet thei
arXiv:2610.09033v1 Announce Type: new Abstract: Standard safety evaluations of large language models assess harmful requests written in canonical plain text, while models in real-world deployment rout
llama: share the nextn tensor flags between models Follow-up of the TODO in glm5-next: move the trunk-only and MTP-only detection that each model copied into a nextn_flags helper of llama_model_base.
arXiv:2610.08200v1 Announce Type: new Abstract: We ask whether specific attention heads, and more finely specific neurons inside those heads, are responsible for recognizing that a language model's co
arXiv:2610.07922v1 Announce Type: cross Abstract: World-action models (WAMs) couple future prediction with robot control, yet existing systems often vary the video backbone, interaction structure, sup
arXiv:2610.07798v1 Announce Type: new Abstract: People increasingly ask large language models what to do with their money, yet seldom describe their finances in full. This paper asks what a model does
arXiv:2610.04198v1 Announce Type: cross Abstract: Diffusion language models (DLMs) enable fast generation by predicting multiple tokens in parallel, but their practical adoption remains limited by a p
arXiv:2610.05790v1 Announce Type: new Abstract: Remote sensing foundation models (RSFMs) are commonly evaluated using aggregate metrics, which can hide systematic performance disparities across ecolog
arXiv:2610.04009v1 Announce Type: cross Abstract: Vision-language-action models (VLAs) inherit strong semantic grounding from pretrained vision-language backbones but are typically optimized for predi
arXiv:2610.06814v1 Announce Type: new Abstract: World models learn to predict how their environment will evolve, making them an important foundation for general-purpose robotic control. Yet world acti
arXiv:2610.02432v1 Announce Type: cross Abstract: Large language models (LLMs) in production systems face prompt injections, trojans (backdoors), and manipulation of automatic quality metrics. This th
arXiv:2610.02486v1 Announce Type: cross Abstract: Typed decision models answer schema-constrained questions about a text in one forward pass and return probabilities meant to be thresholded. We ask wh
arXiv:2610.03137v1 Announce Type: new Abstract: Specifying a goal in language rather than as a goal frame is a natural interface for planning with a latent world model, but testing it needs scenes in
arXiv:2610.03095v1 Announce Type: new Abstract: When two AI agents disagree, who persuades whom? As multi-agent systems increasingly combine language models of different families and sizes, the answer
arXiv:2610.00859v1 Announce Type: new Abstract: World action models (WAMs) jointly predict actions (intent) and visual future (foresight). Standard training adds noise to recorded actions and video si
arXiv:2610.00694v1 Announce Type: cross Abstract: Compression reports summarize how far a compressed language model moved from the dense one, usually by a KL divergence; a deployment that relies on th
arXiv:2603.16065v3 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) has shown strong potential for improving robotic manipulation policies, yet its practical use remains bottlenecked
arXiv:2610.00087v1 Announce Type: cross Abstract: The advancement of natural language processing (NLP) has expanded AI-based text classification in the legal domain. However, accurately classifying le
arXiv:2610.01048v1 Announce Type: new Abstract: World models, which simulate an environment and predict how it changes under actions, are increasingly used in real-world applications such as robotics.
arXiv:2610.01222v1 Announce Type: new Abstract: As generative AI (Gen AI) systems take on increasingly autonomous roles in economically and socially consequential interactions, understanding their pro
arXiv:2609.39441v1 Announce Type: cross Abstract: Online reinforcement learning has been extended to flow matching for diffusion model (DM) image generation. However, this paradigm faces three limitat
arXiv:2609.40071v1 Announce Type: cross Abstract: Digital twins increasingly support downstream analytical tasks that depend on time-series data, motivating interest in time-series foundation models (
arXiv:2609.39341v1 Announce Type: new Abstract: Does a language model merely predict tokens, or does it understand what it says? We make this question measurable by defining 'understanding' through th
arXiv:2609.32720v1 Announce Type: new Abstract: Reward models score responses from large language models (LLMs) and guide LLM training toward human preferences. However, reward models can favor superf
arXiv:2609.34572v1 Announce Type: cross Abstract: Reasoning language models that can call tools must decide during inference whether to answer unaided or delegate. Any self-reflection mechanism for th
arXiv:2609.30979v1 Announce Type: new Abstract: Vision-language models (VLMs) have demonstrated excellent performance in visual tasks, but their visual causal reasoning capabilities still lack reliabl
arXiv:2609.31142v1 Announce Type: cross Abstract: Models trained with reinforcement learning for calibrated decisions (RLCD), such as Jev, answer a typed question about an input, the state, with a pro
Pay attention to System One models if you are building custom harnesses and agentic workflows. Great to see DSPy integrate Jev and now support System One models for calibrating agentic workflows. I'm
arXiv:2609.27327v1 Announce Type: new Abstract: Video provides a rich record of human behavior, interaction, and situated contexts, offering important evidence for understanding people and conducting
arXiv:2609.27166v1 Announce Type: new Abstract: Capability and efficiency are two key dimensions of reasoning in large language models (LLMs). Capability refers to the ability to solve a given problem
arXiv:2609.23178v1 Announce Type: new Abstract: Language models are appealing tools for research on the past. But to trust the evidence a model provides, researchers need to know whether its responses
arXiv:2609.22293v1 Announce Type: new Abstract: Vision-language models (VLMs) and vision-language-action models (VLAs) are increasingly deployed in real-world applications. There, a small perturbation
arXiv:2603.29532v2 Announce Type: replace-cross Abstract: The Linear Parameter-Varying (LPV) framework enables the construction of surrogate models of complex nonlinear and high-dimensional systems, f
arXiv:2609.21509v1 Announce Type: new Abstract: When language models reason in chain-of-thought or exchange free-text intermediates, they serialize structured information into natural language. How mu
arXiv:2602.11244v2 Announce Type: replace Abstract: Video-Language Models (VidLMs) achieve strong benchmark scores, yet these scores often hide whether models use the video at all. We show that VidLM
arXiv:2609.17800v1 Announce Type: new Abstract: Vision-language models (VLMs) remain largely unreliable on panoramic dental radiographs and can rely on learned anatomical priors rather than evidence i
arXiv:2609.18515v1 Announce Type: new Abstract: Safety alignment teaches large language models (LLMs) to recognize harmful requests and reject risky instructions. Yet aligned models can fail when harm
arXiv:2609.19113v1 Announce Type: new Abstract: We evaluate six frontier language models on the two-agent log(N)-Questions game. A questioner sees N Wikipedia lead paragraphs and must identify a secre
arXiv:2609.17644v1 Announce Type: cross Abstract: Domain-specialized language models are widely used for scientific question answering, but stronger general-purpose systems raise a sharper question: w
arXiv:2609.19006v1 Announce Type: cross Abstract: Large Language Models (LLMs) and Large Reasoning Models (LRMs) are typically evaluated on challenging benchmarks through dataset accuracy alone, provi
arXiv:2505.13388v4 Announce Type: replace-cross Abstract: Reward models are essential for aligning language model outputs with human preferences, yet existing approaches often lack both controllabilit
arXiv:2609.14174v1 Announce Type: cross Abstract: Asked to describe what one of six speakers in a recording talks about, audio language models describe the right one on 6 to 16% of trials, below the 1
arXiv:2609.15045v1 Announce Type: cross Abstract: Prompt echoing is a recognized failure mode of instruct language models, in which a model instead of generating a response, mirrors the provided promp
arXiv:2609.12079v1 Announce Type: cross Abstract: Hierarchical correlations are a universal feature of any realistic model of data, and the question of how associative memory models may learn these co
arXiv:2609.10132v1 Announce Type: cross Abstract: The development of generative artificial intelligence resources enables opportunities of speeding up systems and engineering design work. This contrib
Do large language models actually understand the world, or are they just very good at pretending? Does it even matter? Our recent special issue in the Royal Society, “World Models in Natural and Artif
arXiv:2609.10715v1 Announce Type: new Abstract: We introduce NCP-ArchPreview, a latent-space language model that pushes autoregressive pretraining beyond standard next-token prediction (NTP). Alongsid
Recommended read. As the world becomes more agentic, we will start to see world models of different shapes. As an example, I find this “business world model” from @lightfld fascinating as a way to mod
arXiv:2609.07299v1 Announce Type: new Abstract: Learned world models typically assume that observations arrive synchronously, an abstraction inherited from simulators that return a complete state vect
arXiv:2609.03577v1 Announce Type: new Abstract: Language models are commonly discussed as technical artefacts, but they are obviously shaped by the linguistic worlds conveyed by data during their trai
New from the LangSmith Signal. Over the last 2 weeks, we looked at which models teams reach for, and which ones are doing the work. ✅ Reach: gpt-4o-mini was used by 13% of orgs ✅ Work: gpt-4.1-mini sa
arXiv:2609.03774v1 Announce Type: new Abstract: World models have progressed from compact latent dynamics to generative, controllable, and interactive simulators of embodied environments. However, hig
arXiv:2609.00658v1 Announce Type: new Abstract: Metric questions about video require vision-language models to use supplied real-world references to convert visual measurements into physical units. Ye
arXiv:2608.29929v1 Announce Type: new Abstract: Vehicle attribute recognition is an important task in intelligent transportation systems, particularly when Automatic License Plate Recognition (ALPR) i
arXiv:2608.30392v1 Announce Type: new Abstract: Global food security and sustainable climate action increasingly rely on robust, scalable agricultural monitoring. Earth observation foundation models h
arXiv:2608.31133v1 Announce Type: cross Abstract: Neural network mixed-effects models (NMMs) have gained traction by combining the strong representation and predictive power of artificial neural netwo
arXiv:2603.23938v2 Announce Type: replace Abstract: Most testbeds for omni-modal models assess multimodal understanding via textual outputs, leaving it unclear whether these models can properly speak
arXiv:2608.29598v1 Announce Type: new Abstract: We present the first systematic study of the resilience of text-to-video (T2V) diffusion models under random hardware-level faults. While T2V models are