Knowledge catalogue
Anthropic's Claude Code desktop app is strictly optimized for Anthropic's models , creating a 'walled garden' effect that restricts users to Claude exclusively. The redesigned Claude Code desktop app
Iain Martin / Forbes: Mistral, which once aimed for top open models, now leans on being an alternative to Chinese and US labs, says it's on track for $80M in monthly revenue by Dec. — Paris-based Mist
arXiv:2604.15016v1 Announce Type: new Abstract: EEG foundation models (FMs) achieve strong cross-subject and cross-task generalization but impose substantial computational and memory costs that hinder
arXiv:2604.14186v1 Announce Type: cross Abstract: Large self-supervised speech (SSL) models achieve strong downstream performance, but their size limits deployment in resource-constrained settings. We
arXiv:2604.15311v1 Announce Type: new Abstract: This paper focuses on the alignment of flow matching models with human preferences. A promising way is fine-tuning by directly backpropagating reward gr
This hands-on guide walks through every step of fine-tuning an Amazon Nova model with the Amazon Nova Forge SDK, from data preparation to training with data mixing to evaluation, giving you a repeatab
arXiv:2508.05015v2 Announce Type: replace Abstract: Large language models (LLMs) have shown strong reasoning capabilities when fine-tuned with reinforcement learning (RL). However, such methods requir
arXiv:2509.15602v5 Announce Type: replace Abstract: Multimodal large language models (MLLMs) excel at general video understanding but struggle with fast, high-frequency sports like tennis, where rally
arXiv:2604.15188v1 Announce Type: new Abstract: Visual token pruning methods effectively mitigate the quadratic computational growth caused by processing high-resolution images and video frames in vis
arXiv:2604.13440v1 Announce Type: new Abstract: Deploying Large Language Models (LLMs) on edge devices faces severe computational and memory constraints, limiting real-time processing and on-device in
arXiv:2511.10946v3 Announce Type: replace Abstract: Vision-language models (VLMs) struggle with 3D-related tasks such as spatial cognition and physical understanding, which are crucial for real-world
arXiv:2601.04442v2 Announce Type: replace-cross Abstract: Large Vision-Language Models (LVLMs) have exhibited strong reasoning capabilities through chain-of-thought mechanisms that generate step-by-st
arXiv:2604.13068v1 Announce Type: new Abstract: When do large language models decide to hallucinate? Despite serious consequences in healthcare, law, and finance, few formal answers exist. Recent work
arXiv:2604.14044v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) excel in general vision-language tasks, their application to remote sensing change understanding is hinde
arXiv:2511.11334v3 Announce Type: replace Abstract: The rapid advancement of large language models (LLMs) has not been matched by their evaluation in low-resource languages, especially Southeast Asian
arXiv:2604.13287v1 Announce Type: new Abstract: Weight pruning is a common technique for compressing large neural networks. We focus on the challenging post-training one-shot setting, where a pre-trai
arXiv:2505.07591v2 Announce Type: replace Abstract: Instruction following refers to the ability of large language models (LLMs) to generate outputs that satisfy all specified constraints. Existing res
arXiv:2604.13993v1 Announce Type: cross Abstract: Physical reasoning over visual inputs demands tight integration of visual perception, domain knowledge, and multi-step symbolic inference. Yet even st
arXiv:2604.02486v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) have achieved impressive performance across a wide range of multimodal tasks. However, they often fail on tasks
arXiv:2503.23137v2 Announce Type: replace-cross Abstract: Understanding humor-particularly when it involves complex, contradictory narratives that require comparative reasoning-remains a significant c
arXiv:2604.12447v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models inherit rich world knowledge from vision-language backbones and acquire executable skills via action demonstrations.
arXiv:2604.12537v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have achieved remarkable progress in multimodal understanding, yet their positional encoding mechanisms remain suboptima
arXiv:2604.12076v1 Announce Type: cross Abstract: The Identifiable Victim Effect (IVE) - the tendency to allocate greater resources to a specific, narratively described victim than to a statistically
arXiv:2604.12582v1 Announce Type: new Abstract: Recent Video Large Language Models (Video-LLMs) have demonstrated strong capability in video understanding, yet they still suffer from hallucinations. E
arXiv:2601.09313v2 Announce Type: replace-cross Abstract: Language models perform well on grammatical agreement, but it is unclear whether this reflects rule-based generalization or memorization. We s
arXiv:2509.17995v2 Announce Type: replace-cross Abstract: Recent advances have shown that scaling test-time computation enables large language models (LLMs) to solve increasingly complex problems acro
arXiv:2510.21697v2 Announce Type: replace Abstract: In this paper we show that visual diffusion models can serve as effective geometric solvers: they can directly reason about geometric problems by wo
arXiv:2510.20635v2 Announce Type: replace-cross Abstract: Curiosity serves as a pivotal conduit for human beings to discover and learn new knowledge. Recent advancements of large language models (LLMs
arXiv:2505.18931v4 Announce Type: replace Abstract: Understanding and inferring causal relationships from texts is a core aspect of human cognition and is essential for advancing large language models
arXiv:2503.21380v3 Announce Type: replace Abstract: The rapid advancement of large reasoning models has saturated existing math benchmarks, underscoring the urgent need for more challenging evaluation
arXiv:2604.10627v1 Announce Type: cross Abstract: How the brain supports language across different languages is a basic question in neuroscience and a useful test for multilingual artificial intellige
arXiv:2604.09750v1 Announce Type: cross Abstract: Large Reasoning Models (LRMs) have achieved remarkable performance across diverse domains, yet their decision-making under conflicting objectives rema
arXiv:2604.09945v1 Announce Type: cross Abstract: The rapid adoption of large vision-language models (LVLMs) in recent years has been accompanied by growing fairness concerns due to their propensity t
arXiv:2604.11240v1 Announce Type: new Abstract: Token pruning has emerged as an effective approach to reduce the substantial computational overhead of Large Vision-Language Models (LVLMs) by discardin
arXiv:2601.03926v2 Announce Type: replace Abstract: The deployment of Large Vision-Language Models (LVLMs) for real-world document question answering is often constrained by dynamic, user-defined poli
arXiv:2604.09861v1 Announce Type: new Abstract: Text-to-image diffusion models exhibit strong generative performance but remain highly sensitive to prompt formulation, often requiring extensive manual
arXiv:2604.11778v1 Announce Type: cross Abstract: Contemporary large language models (LLMs) have demonstrated remarkable reasoning capabilities, particularly in specialized domains like mathematics an
New post: We show that small, cheap models can detect the flagship Mythos FreeBSD zero-day (CVE-2026-4747) using a simple harness we call nano-analyzer Models down to 3.6B active params (including ope
arXiv:2604.10551v1 Announce Type: new Abstract: This paper presents an overview of the NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models. This challenge utili
arXiv:2512.07222v3 Announce Type: replace-cross Abstract: To address the trade-off between robustness and performance for robust VLM, we observe that function words could incur vulnerability of VLMs a
arXiv:2410.13987v3 Announce Type: replace Abstract: Answering complex real-world questions in the medical domain often requires accurate retrieval from medical Textual Knowledge Graphs (medical TKGs),
arXiv:2505.15489v4 Announce Type: replace-cross Abstract: The impact of multimodal misinformation arises not only from factual inaccuracies but also from the misleading narratives that creators delibe
arXiv:2604.11050v1 Announce Type: cross Abstract: We extract 21-emotion vector sets from twelve small language models (six architectures x base/instruct, 1B-8B parameters) under a unified comprehensio
arXiv:2409.02231v5 Announce Type: replace-cross Abstract: We show that large language model (LLMs) can be transformed via supervised fine-tuning (SFT) of engineered prompts into SmileyLlama for explor
arXiv:2602.16309v2 Announce Type: replace-cross Abstract: Fault injection attacks on embedded neural network models have been shown as a potent threat. Numerous works studied resilience of models from
arXiv:2510.27269v3 Announce Type: replace-cross Abstract: Reasoning language models (RLMs) achieve strong performance on complex reasoning tasks, yet they still exhibit a multilingual reasoning gap, p
arXiv:2604.04161v2 Announce Type: replace Abstract: In Vision-Language-Action (VLA) models, action chunking (i.e., executing a sequence of actions without intermediate replanning) is a key technique t
arXiv:2604.08983v1 Announce Type: new Abstract: Spatial reasoning is a fundamental capability for embodied intelligence, especially for fine-grained manipulation tasks such as robotic assembly. While
arXiv:2604.08867v1 Announce Type: cross Abstract: Audio has rapidly become a primary interface for foundation models, powering real-time voice assistants. Ensuring safety in audio systems is inherentl
arXiv:2604.08757v1 Announce Type: cross Abstract: Humor is one of the most culturally embedded and socially significant dimensions of human communication, yet it remains largely unexplored as a dimens
arXiv:2604.08723v1 Announce Type: cross Abstract: Preference optimization methods such as DPO and KTO are widely used for aligning language models, yet little is understood about what properties of pr
arXiv:2512.02826v3 Announce Type: replace-cross Abstract: Flow-based diffusion models have emerged as a leading paradigm for training generative models across images and videos. However, their memoriz
arXiv:2604.06165v2 Announce Type: replace Abstract: Large vision-language models can produce object hallucinations in image descriptions, highlighting the need for effective detection and mitigation s
arXiv:2604.08970v1 Announce Type: cross Abstract: We study predictive multilingual evaluation: estimating how well a model will perform on a task in a target language when direct benchmark results are
arXiv:2604.08828v1 Announce Type: cross Abstract: Classifier-free Guidance (CFG) lets practitioners trade-off fidelity against diversity in Diffusion Models (DMs). The practicality of CFG is however h
arXiv:2604.08941v1 Announce Type: new Abstract: Medical Vision Language Models VLMs suffer from two failure modes that threaten safe deployment mis calibrated confidence and sensitivity to question re
arXiv:2505.12509v3 Announce Type: replace-cross Abstract: Post-hoc explanations provide transparency and are essential for guiding model optimization, such as prompt engineering and data sanitation. H
arXiv:2604.08761v1 Announce Type: new Abstract: Sign language recognition suffers from catastrophic scaling failure: models achieving high accuracy on small vocabularies collapse at realistic sizes. E
arXiv:2604.09519v1 Announce Type: new Abstract: World models have emerged as a unifying paradigm for learning latent dynamics, simulating counterfactual futures, and supporting planning under uncertai
arXiv:2604.09227v1 Announce Type: cross Abstract: Image generative models have become indispensable tools to yield exquisite high-resolution (HR) images for everyone, ranging from general users to pro