Knowledge catalogue
arXiv:2604.11087v1 Announce Type: new Abstract: Despite the groundbreaking advancements made by large language models (LLMs), hallucination remains a critical bottleneck for their deployment in high-s
arXiv:2604.11512v1 Announce Type: cross Abstract: The growing demand for deploying Small Language Models (SLMs) on edge devices, including laptops, smartphones, and embedded platforms, has exposed fun
Pharma artificial intelligence startup Helical Ltd. announced today that it has raised 10 million in new funding to expand its virtual AI lab platform, which turns biological foundation models into re
arXiv:2603.02578v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed in socially sensitive domains, yet their unpredictable behaviors, ranging from misalign
arXiv:2604.11609v1 Announce Type: new Abstract: Large language models exhibit sycophantic tendencies--validating incorrect user beliefs to appear agreeable. We investigate whether this behavior varies
Is there somewhere a collection of the best agent/coding harnesses for each models, especially open-source and local ones? In my opinion, the biggest reason why people are struggling with open/local m
It is going to be like what happened in coding: as soon as models crossed a certain threshold (Opus 4.5, GPT-5.2, Gemini 3), suddenly Claude Code & Codex were viable. Before that, it was all about cod
arXiv:2604.09712v1 Announce Type: cross Abstract: Spatial reasoning is a cornerstone capability for intelligent systems to perceive and interact with the physical world. However, multimodal large lang
let's go open-source and local models! Uber's CTO told @LauraBratton5 that AI coding tools—particularly Anthropic’s Claude Code—has already maxed out its 2026 AI budget 📈 “I'm back to the drawing boar
arXiv:2510.12117v3 Announce Type: replace-cross Abstract: Chatbot service providers (e.g., OpenAI) rely on tiered subscription plans to generate revenue, offering black-box access to basic models for
arXiv:2604.11575v1 Announce Type: new Abstract: Pixel-based language models are gaining momentum as alternatives to traditional token-based approaches, promising to circumvent tokenization challenges.
arXiv:2604.09824v1 Announce Type: cross Abstract: Vision language action (VLA) models enable generalist robotic agents but often exhibit language ignorance, relying on visual shortcuts and remaining i
arXiv:2604.09624v1 Announce Type: new Abstract: Large language models (LLMs) are systematically overconfident: they routinely express high certainty on questions they often answer incorrectly. Existin
arXiv:2604.10027v1 Announce Type: new Abstract: Large language models (LLMs) suffer from hallucination and context forgetting. Prior studies suggest that attention drift is a primary cause of these pr
arXiv:2603.27960v2 Announce Type: replace-cross Abstract: Although Large Vision Language Models (LVLMs) have demonstrated impressive multimodal reasoning capabilities, their scalability and deployment
arXiv:2512.17270v2 Announce Type: replace-cross Abstract: Role-playing models (RPMs) are widely used in real-world applications but underperform when deployed in the wild. This degradation can be attr
Carl Franzen / VentureBeat: Users accuse Anthropic of degrading Claude Opus 4.6's and Claude Code's performance; the startup's employees publicly deny it degrades models to manage capacity — A growing
arXiv:2604.10970v1 Announce Type: new Abstract: Background: Task-specific microscopy datasets are often small, making it difficult to train deep learning models that learn robust features. While self-
arXiv:2601.06165v2 Announce Type: replace-cross Abstract: Current vision-language benchmarks predominantly feature well-structured questions with clear, explicit prompts. However, real user queries ar
arXiv:2604.02458v2 Announce Type: replace-cross Abstract: Behavioral simulation is increasingly used to anticipate responses to interventions. Large language models (LLMs) enable researchers to specif
arXiv:2604.09208v1 Announce Type: cross Abstract: We develop a predictive-first optimisation framework for streaming hidden Markov models. Unlike classical approaches that prioritise full posterior re
arXiv:2511.18960v3 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have shown remarkable progress in embodied tasks recently, but most methods process visual observations in
arXiv:2604.09201v1 Announce Type: new Abstract: Camera-controllable video generation aims to synthesize videos with flexible and physically plausible camera movements. However, existing methods either
arXiv:2503.14075v3 Announce Type: replace-cross Abstract: Large vision-language models (VLMs) have demonstrated remarkable capabilities in open-world multimodal understanding, yet their high computati
arXiv:2604.08976v1 Announce Type: new Abstract: We report that model quantisation restructures domain-level metacognitive efficiency in LLMs rather than degrading it uniformly. Evaluating Llama-3-8B-I
arXiv:2604.09436v1 Announce Type: new Abstract: Diffusion models trained on noisy datasets often reproduce high-frequency training artifacts, significantly degrading generation quality. To address thi
arXiv:2604.09529v1 Announce Type: cross Abstract: Large Vision Language Models (LVLMs) achieve strong multimodal reasoning but frequently exhibit hallucinations and incorrect responses with high certa
arXiv:2604.07258v1 Announce Type: new Abstract: In this growing age of data and technology, large black-box models are becoming the norm due to their ability to handle vast amounts of data and learn i
arXiv:2604.06201v1 Announce Type: cross Abstract: While most reading comprehension benchmarks for LLMs focus on factual information that can be answered by localizing specific textual evidence, many r
arXiv:2604.08527v1 Announce Type: new Abstract: On-policy distillation (OPD) trains student models under their own induced distribution while leveraging supervision from stronger teachers. We identify
arXiv:2604.06871v1 Announce Type: cross Abstract: Large Speech Language Models (LSLMs) typically operate at high token rates (tokens/s) to ensure acoustic fidelity, yet this results in sequence length
arXiv:2604.08456v1 Announce Type: cross Abstract: Despite rapid progress, pretrained vision-language models still struggle when answers depend on tiny visual details or on combining clues spread acros
arXiv:2604.08476v1 Announce Type: new Abstract: Multimodal reasoning models (MRMs) trained with reinforcement learning with verifiable rewards (RLVR) show improved accuracy on visual reasoning benchma
I'm releasing the 34 slides on how we design and train best-in-class edge models at @liquidai I presented these slides yesterday at @aiDotEngineer They cover model architecture, pre-training, scaling
arXiv:2604.07802v1 Announce Type: new Abstract: Large-scale vision-language models (VLMs) exhibit remarkable zero-shot capabilities, yet the internal mechanisms driving their anomaly detection (AD) pe
arXiv:2604.08333v1 Announce Type: new Abstract: The rise of multimodal large language models (MLLMs) has sparked an unprecedented wave of applications in the field of medical imaging analysis. However
arXiv:2603.04300v2 Announce Type: replace Abstract: Foundation models in general promise to accelerate scientific computation by learning reusable representations across problem instances, yet constra
arXiv:2601.04068v3 Announce Type: replace Abstract: Aligning text-to-video diffusion models with human preferences is crucial for generating high-quality videos. Existing Direct Preference Otimization
arXiv:2604.07914v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable success across cross-modal tasks but remain hindered by hallucinations, producing textual
arXiv:2604.07506v1 Announce Type: cross Abstract: Reward Models (RMs) are critical components in the Reinforcement Learning from Human Feedback (RLHF) pipeline, directly determining the alignment qual
arXiv:2604.08243v1 Announce Type: new Abstract: Although Large Language Models (LLMs) demonstrate remarkable reasoning capabilities, inherent social biases often cascade throughout the Chain-of-Though
arXiv:2604.06206v1 Announce Type: cross Abstract: This study seeks to uncover evidence of a latent structure in evolved human culture as it is refracted through contemporary large language models (LLM
arXiv:2610.21459v1 Announce Type: cross Abstract: Unified multimodal models (UMMs) receive image-generation supervision that exposes them to visual information not fully documented in text. Can learni
arXiv:2610.20679v1 Announce Type: new Abstract: Representation-based safety defenses for vision-language models (VLMs) often learn to separate harmful from benign inputs, but separation alone does not
arXiv:2610.22356v1 Announce Type: new Abstract: Vision-language models still struggle to understand 3D spatial relations across views and update spatial judgments as the observer moves. A common appro
arXiv:2610.20989v1 Announce Type: cross Abstract: Improving the reasoning capabilities of vision-language models (VLMs) often relies on post-training with supervision from stronger models. Two common
arXiv:2610.20887v1 Announce Type: new Abstract: Fine-tuning language models on narrowly defined harmful tasks can induce emergent misalignment (EM) across unrelated domains. While prior work has ident
arXiv:2610.20636v1 Announce Type: cross Abstract: Sampling from continuous flow-based generators such as flow matching models requires numerical ODE or SDE integration, making inference cost depend on
arXiv:2610.21750v1 Announce Type: cross Abstract: Artificial intelligence systems deployed in high-risk settings increasingly require models that support meaningful human oversight. Concept-based mode
arXiv:2508.17715v2 Announce Type: replace-cross Abstract: As more content generated by large language models (LLMs) floods into the Internet, information retrieval (IR) systems now face the challenge
arXiv:2610.21612v1 Announce Type: new Abstract: Learning intrinsic dynamics---the relationship between actions and their consequences---is essential for world models. However, visual variations unrela
arXiv:2610.22087v1 Announce Type: new Abstract: In pathology, pattern recognition relies on a frame of reference built through extensive training and experience, which may still fall short when encoun
arXiv:2507.19839v2 Announce Type: replace-cross Abstract: The modality gap is intrinsic to multimodal alignment, where embeddings from different modalities remain partially separated in a shared repre
arXiv:2610.21477v1 Announce Type: new Abstract: Medical calculators translate raw patient observations into clinically actionable values and scores. However, applying these calculators directly to fre
Until we solve the alignment problem at its source, AI models will continue to optimize for the wrong goals, and increasingly impactful real-world consequences may occur, beyond the ones described her
arXiv:2610.22311v1 Announce Type: new Abstract: Video world models turn actions and camera motion into long visual rollouts, making video a natural interface for interactive simulation. Such interacti
arXiv:2509.20645v4 Announce Type: replace Abstract: Modern ML research increasingly faces an evaluation bottleneck: building benchmarks and running experiments is costly, slowing iteration. We ask how
arXiv:2610.19721v1 Announce Type: cross Abstract: Language captures only a subset of the perceptions, intuitions and intents that form meaning between speakers. What, then, are the limits of language?
arXiv:2610.20157v1 Announce Type: new Abstract: World Action Models (WAMs) typically adapt video foundation models to robotic control through joint video and action prediction. However, task-level ins
arXiv:2610.17672v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong potential for human mobility generation by modeling individual routines, activities, and mobility prefere