Knowledge catalogue
I came up with a somewhat foolish new benchmark for testing image generation models, to exercise the new ChatGPT Images 2.0: 'Do a where's Waldo style image but it's where is the raccoon holding a ham
I find that open weights models over-perform on benchmarks compared to actual real-world usage, and Kimi feels like no exception. For example, a small amount of use will show that Kimi is not as good
arXiv:2604.16405v1 Announce Type: cross Abstract: Video-generative world models are increasingly used as neural simulators for embodied planning and policy learning, yet their ability to predict physi
arXiv:2604.17651v1 Announce Type: new Abstract: World models, generative AI systems that simulate how environments evolve, are transforming autonomous driving, yet all existing approaches adopt an ego
arXiv:2507.09025v4 Announce Type: replace Abstract: We propose Lizard, a linearization framework that transforms pretrained Transformer-based Large Language Models (LLMs) into subquadratic architectur
arXiv:2401.15604v4 Announce Type: replace Abstract: Diffusion models have become a leading paradigm in generative AI, with score estimation via denoising score matching as a central component. While r
arXiv:2508.14461v3 Announce Type: replace Abstract: While multi-step diffusion models have advanced both forward and inverse rendering, existing approaches often treat these problems independently, le
arXiv:2604.17132v1 Announce Type: new Abstract: Safety-aligned large language models (LLMs) often generate refusal responses to harmless queries due to the over-refusal problem. However, existing meth
arXiv:2502.02871v2 Announce Type: replace Abstract: Scientific reasoning, the process through which humans apply logic, evidence, and critical thinking to explore and interpret scientific phenomena, i
arXiv:2604.17957v1 Announce Type: new Abstract: Process Reward Models (PRMs) have emerged as a powerful tool for providing step-level feedback when evaluating the reasoning of Large Language Models (L
arXiv:2604.17243v1 Announce Type: new Abstract: A robust Multimodal Large Language Model (MLLM) for Earth Observation should maintain consistent interpretation and reasoning under realistic input vari
arXiv:2510.09351v2 Announce Type: replace Abstract: While Small Language Models (SLMs) have demonstrated promising performance on an increasingly wide array of commonsense reasoning benchmarks, curren
arXiv:2604.16557v1 Announce Type: cross Abstract: Current post-training methodologies for adapting Large Vision-Language Models (LVLMs) generally fall into two paradigms: Supervised Fine-Tuning (SFT)
arXiv:2604.17873v1 Announce Type: new Abstract: Video Large Language Models (Vid-LLMs) have demonstrated remarkable performance in video understanding tasks, yet their robustness under conversational
arXiv:2512.07407v2 Announce Type: replace Abstract: Language models frequently produce plausible yet incorrect reasoning traces that are difficult to verify. We investigate fine-tuning models to use P
arXiv:2506.00065v2 Announce Type: replace Abstract: Multimodal language models (MLMs) increasingly demonstrate human-like communication, yet their use of everyday perspectival words remains poorly und
arXiv:2505.23941v4 Announce Type: replace-cross Abstract: Large language models (LLMs) memorize a vast amount of prior knowledge from the Internet that helps them on downstream tasks but also may noto
arXiv:2604.18249v1 Announce Type: new Abstract: Speech encoder models are known to model members of some speaker groups (SGs) better than others. However, there has been little work in establishing wh
arXiv:2604.15508v1 Announce Type: cross Abstract: LLMbench is a browser-based workbench for the comparative close reading of large language model (LLM) outputs. Where existing tools for LLM comparison
arXiv:2601.05201v2 Announce Type: replace-cross Abstract: Large vision-language models (VLMs) are highly capable, yet often hallucinate by favoring textual prompts over visual evidence. We study this
arXiv:2511.13131v2 Announce Type: replace Abstract: Large Language Models (LLMs) have emerged as powerful tools for automating complex reasoning and decision-making tasks. In telecommunications, they
arXiv:2511.10262v3 Announce Type: replace-cross Abstract: Full-Duplex Speech Language Models (FD-SLMs) enable real-time, overlapping conversational interactions, offering a more dynamic user experienc
arXiv:2604.15967v1 Announce Type: cross Abstract: Despite the remarkable synthesis capabilities of text-to-image (T2I) models, safeguarding them against content violations remains a persistent challen
We’re launching Kimi K2.6 on Fireworks as a Day-0 launch partner! K2.5 was the base for standout models like @Cursor’s Composer 2 and was the most popular model on our training platform. K2.6 on Firew
arXiv:2602.16716v3 Announce Type: replace Abstract: Contextuality is a central feature of quantum theory, traditionally understood as the impossibility of reproducing quantum measurement statistics us
arXiv:2410.01540v4 Announce Type: replace Abstract: Classical diffusion models typically rely on isotropic Gaussian noise, treating all regions uniformly and overlooking structural information importa
arXiv:2604.14640v1 Announce Type: new Abstract: The proliferation of financial misinformation poses a severe threat to market stability and investor trust, misleading market behavior and creating crit
arXiv:2604.14262v1 Announce Type: new Abstract: GUI grounding models report over 85% accuracy on standard benchmarks, yet drop 27-56 percentage points when instructions require spatial reasoning rathe
A guide on disabling thinking mode in Ollama models using the CLI by running models with the `--think=false` flag or using `/set nothink` followed by a prompt. The post likely discusses how to configu
arXiv:2603.17512v4 Announce Type: replace Abstract: Large language models (LLMs) exhibit strong general intelligence, yet their multilingual performance remains highly imbalanced. Although LLMs encode
arXiv:2601.14053v2 Announce Type: replace-cross Abstract: The field of artificial intelligence has undergone a revolution from foundational Transformer architectures to reasoning-capable systems appro
arXiv:2604.14866v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have demonstrated significant potential in medical image analysis, yet their application in intraoral photography remains
arXiv:2604.14672v1 Announce Type: new Abstract: Large language models (LLMs) are being increasingly used in urban planning, but since gendered space theory highlights how gender hierarchies are embedd
arXiv:2604.14629v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have shown remarkable capabilities in joint vision-language understanding, but their large scale poses significant challen
arXiv:2604.13715v1 Announce Type: cross Abstract: Large Audio-Language Models (LALMs) enable general audio understanding and demonstrate remarkable performance across various audio tasks. However, the
What folk don’t get is that the play of Anthropic et al is to get enterprises to use their models via their own wrapper hooked into systems of record This is why they are moving from per seat pricing
arXiv:2604.13824v1 Announce Type: new Abstract: World models have been emerging as critical components for assessing the consequences of actions generated by interactive agents in online planning and
arXiv:2604.13077v1 Announce Type: new Abstract: Coronary angiography (CAG) reports contain clinically relevant physiological measurements, yet this information is typically in the form of unstructured
arXiv:2604.13882v1 Announce Type: new Abstract: The evaluation of supervised machine learning models is a critical stage in the development of reliable predictive systems. Despite the widespread avail
arXiv:2601.11329v3 Announce Type: replace Abstract: Spoken conversational systems require more than accurate speech generation to have human-like conversations: to feel natural and engaging, they must
arXiv:2604.13540v1 Announce Type: new Abstract: Unified Multimodal Models (UMMs) aim to integrate visual understanding and generation within a single structure. However, these models exhibit a notable
Models are getting smaller, smarter and Apache licensed. Love to see Gemma and Qwen doing it. Qwen 3.6 is here, and open-source! Run it locally with improved agentic coding capabilities. Try it with C
arXiv:2603.07083v2 Announce Type: replace Abstract: Model-based reinforcement learning (MBRL) agents operating in high-dimensional observation spaces, such as Dreamer, rely on learning abstract repres
arXiv:2409.06679v3 Announce Type: replace Abstract: Processing long contexts is increasingly important for Large Language Models (LLMs) in tasks like multi-turn dialogues, code generation, and documen
arXiv:2604.12596v1 Announce Type: cross Abstract: We introduce KumoRFM-2, the next iteration of a pre-trained foundation model for relational data. KumoRFM-2 supports in-context learning as well as fi
arXiv:2502.17403v5 Announce Type: replace-cross Abstract: Electronic Health Records (EHRs) offer considerable potential for clinical prediction, but their complexity and heterogeneity challenge tradit
arXiv:2507.22359v4 Announce Type: replace Abstract: Although large language models (LLMs) have shown exceptional capabilities across a wide range of tasks, reliable evaluation remains a critical chall
A mid-2026 outlook piece from the Interconnects AI newsletter in which the author makes specific predictions about the trajectory of open-weight language models, likely covering expected capability mi
arXiv:2604.12446v1 Announce Type: cross Abstract: Text-to-image (T2I) diffusion models have achieved remarkable success in image synthesis, but their reliance on large-scale data and open ecosystems i
Small models are cheap to run, but expensive to adapt. The hard part is not only fine-tuning. It is the surrounding loop that involves collecting data, diagnosing failures, building evals, avoiding re
arXiv:2604.12617v1 Announce Type: cross Abstract: The post-training pipeline for diffusion models currently has two stages: supervised fine-tuning (SFT) on curated data and reinforcement learning (RL)
arXiv:2603.18846v2 Announce Type: replace Abstract: Foundation models are used to extract transferable representations from large amounts of unlabeled data, typically via self-supervised learning (SSL
The Ollama Cloud Subscription includes a feature described as 'Run cloud models at a time,' which refers to how many AI models a user can have simultaneously loaded and running in the cloud at any giv
arXiv:2504.14988v3 Announce Type: replace Abstract: Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated remarkable multimodal perception capabilities, garnering significant a
arXiv:2604.10597v1 Announce Type: cross Abstract: State Space Models (SSMs), represented by the Mamba family, provide linear-time sequence modeling and are attractive for long-context inference. Yet p
arXiv:2604.10514v1 Announce Type: cross Abstract: Surgical phase segmentation is central to computer-assisted surgery, yet robust models remain difficult to develop when labeled surgical videos are sc
arXiv:2604.10014v1 Announce Type: cross Abstract: This paper provides a comprehensive evaluation of demographic and linguistic biases in omnimodal language models that process text, images, audio, and
arXiv:2604.10567v1 Announce Type: cross Abstract: Diffusion-based language models (dLLMs) have emerged as a promising alternative to autoregressive language models, offering the potential for parallel
arXiv:2604.11576v1 Announce Type: new Abstract: Despite their impressive zero-shot abilities, vision-language models such as CLIP have been shown to be susceptible to adversarial attacks. To enhance i
arXiv:2512.18073v2 Announce Type: replace Abstract: Multimodal LLMs (MLLMs) are capable of performing complex data analysis, visual question answering, generation, and reasoning tasks. However, their