Knowledge catalogue
arXiv:2605.16239v1 Announce Type: new Abstract: We introduce a dynamics-level approach to watermarking generative models. Rather than embedding signals into model weights or outputs, we embed the wate
arXiv:2605.15249v1 Announce Type: cross Abstract: AI models are increasingly deployed in cloud-native environments to support scalable and automated services. However, while platforms such as Kubernet
arXiv:2603.25099v2 Announce Type: replace-cross Abstract: We present a framework in which a large language model (LLM) acts as an online adaptive controller for SIMP topology optimization, replacing c
llama.cpp with MTP support makes local models fast enough to use as daily drivers 🚀 Qwen3.6-27B dense generation (on A10G): From 25 tok/s → 45 tok/s (+78%). Two flags on llama-server: --spec-type draf
arXiv:2605.15572v1 Announce Type: new Abstract: The dynamic range of activations is a first-order constraint for low-bit quantization, activation scaling, and stable LLM inference. Prior work characte
arXiv:2605.15603v1 Announce Type: cross Abstract: Model-based reinforcement learning (RL) offers a compelling approach to offline RL by enabling value learning on imagined on-policy trajectories. Howe
One thing to watch for with Claude & GPT is that the models expose too much irrelevant history in their outputs. Slides are given footers saying things like 'Better, more targeted version' if you aske
arXiv:2605.15256v1 Announce Type: new Abstract: Current game world models simulate environments from a subjective, player-centric perspective. However, by treating the Non-Player Character (NPC) merel
arXiv:2605.15454v1 Announce Type: new Abstract: Reasoning-trained language models often spend more tokens on harder problems, but longer chains of thought do not show whether a model is merely computi
arXiv:2605.15792v1 Announce Type: new Abstract: The long-standing goal of multimodal AI is to build unified models in which visual understanding and visual generation mutually enhance one another. Des
arXiv:2605.15607v1 Announce Type: new Abstract: Large language models (LLMs) achieve high pass rates on code generation benchmarks, yet whether they can transfer this ability to languages absent from
arXiv:2602.08324v3 Announce Type: replace Abstract: Chain-of-Thought (CoT) reasoning successfully enhances the reasoning capabilities of Large Language Models (LLMs), yet it incurs substantial computa
We causally trained a lot of SOTA search models internally, shall we make some small release from time to time 🤣🤣 @bo_wangbo stealth releasing probably the strongest open multilingual ColBERT (and it'
arXiv:2605.14631v1 Announce Type: cross Abstract: We introduce Action-Inspired Generative Models (AGMs), a dual-network generative framework motivated by the observation that existing bridge-matching
arXiv:2605.14897v1 Announce Type: cross Abstract: Despite many successful attempts at explaining Deep Reinforcement Learning policies using distillation, it remains difficult to balance the performanc
arXiv:2605.14906v1 Announce Type: new Abstract: Memory is essential for large vision-language models (LVLMs) to handle long, multimodal interactions, with two method directions providing this capabili
arXiv:2605.14938v1 Announce Type: cross Abstract: Continual learning in multimodal large language models (MLLMs) aims to sequentially acquire knowledge while mitigating catastrophic forgetting, yet ex
arXiv:2512.21651v2 Announce Type: replace Abstract: Large Language Models (LLMs) deliver strong performance across a wide range of NLP tasks, but their massive sizes hinder deployment on resource-cons
arXiv:2505.09552v3 Announce Type: replace-cross Abstract: Mixed-effects models are widely used to model data with hierarchical grouping structures and high-cardinality categorical predictor variables.
arXiv:2605.15026v1 Announce Type: cross Abstract: Online OS tuning can improve long-running services, but existing controllers are poorly matched to live hosts. They treat scheduler, power, memory, an
arXiv:2605.14636v1 Announce Type: new Abstract: Large language models (LLMs) often fail to reason under temporal cutoffs: when prompted to answer from the standpoint of an earlier time, they exploit k
arXiv:2605.14570v1 Announce Type: new Abstract: Large Language Diffusion Models (LLDMs) are emerging as an alternative to autoregressive models, offering faster inference through higher parallelism. S
arXiv:2406.05410v3 Announce Type: replace Abstract: Current multimodal large language models (MLLMs) are mainly focused on the understanding and processing of perceptual modalities such as images and
arXiv:2511.15743v2 Announce Type: replace Abstract: Operational forecasting of the ionosphere remains a critical space weather challenge due to sparse observations, complex coupling across geospatial
arXiv:2605.13115v1 Announce Type: cross Abstract: Diffusion models depend on pseudo-random number generators (PRNGs) for latent noise sampling. We present DiffusionHijack, a supply-chain backdoor atta
arXiv:2605.12574v1 Announce Type: cross Abstract: Vision-language models (VLMs) are trained on large-scale image-text corpora that may contain private, copyrighted, or otherwise sensitive data, motiva
arXiv:2510.18114v3 Announce Type: replace-cross Abstract: Discrete diffusion models have emerged as a powerful class of models and a promising route to fast language generation, but practical implemen
Like any AI dev not employed by a closed lab, we share the ambition that at least 10x more should be capable of training frontier models in 2026. And like we all know, some 10x leaps can't survive a c
arXiv:2605.13163v1 Announce Type: cross Abstract: Foundation models and low-rank adapters enable efficient on-device generative AI but raise risks such as intellectual property leakage and model recov
arXiv:2603.19185v2 Announce Type: replace Abstract: Synthetic data is often perceived as a silver-bullet solution to data anonymization and privacy-preserving data publishing. Drawn from generative mo
arXiv:2605.12940v1 Announce Type: cross Abstract: Probabilistic Circuits (PCs) are deep generative models that support exact and efficient probabilistic inference. Yet in autoregressive language model
arXiv:2605.12904v1 Announce Type: new Abstract: Tabular foundation models (TFMs) have emerged as a powerful paradigm for in-context learning on structured data, enabling direct prediction on new tabul
arXiv:2605.11091v1 Announce Type: new Abstract: Automated ASD screening tools remain limited by single-architecture evaluations, axis-restricted assessment, and near-exclusive focus on adult cohorts,
arXiv:2605.11726v1 Announce Type: new Abstract: Recently, reinforcement learning (RL) has been widely applied during post-training for diffusion large language models (dLLMs) to enhance reasoning with
arXiv:2601.21944v2 Announce Type: replace Abstract: The widespread adoption of deep learning models in computer vision has intensified concerns about interpretability. Despite strong performance, thes
arXiv:2605.12374v1 Announce Type: new Abstract: Visual latent reasoning lets a multimodal large language model (MLLM) create intermediate visual evidence as continuous tokens, avoiding external tools
arXiv:2603.28561v2 Announce Type: replace Abstract: The growing deployment of small Unmanned Aerial Systems (sUASs) in low-altitude airspaces has increased the need for reliable tactical deconfliction
arXiv:2602.15451v3 Announce Type: replace-cross Abstract: Deep generative modeling to stochastically design small molecules is an emerging technology for accelerating drug discovery and development. H
arXiv:2605.12289v1 Announce Type: new Abstract: Leveraging the rich world knowledge of Large Language Models (LLMs) to enhance Reinforcement Learning (RL) agents offers a promising path toward general
This research paper from Sakana AI and NVIDIA explores techniques for creating more efficient transformer language models by reducing sparsity, computational requirements, and model size while maintai
arXiv:2605.11494v1 Announce Type: new Abstract: Distilled one-step (T=1) or few-step (Tleq4) diffusion models enable real-time image generation but often exhibit reduced sample diversity compared to t
arXiv:2605.11634v1 Announce Type: new Abstract: Although Vision Language Models (VLMs) have seen tremendous progress across all kinds of use cases, they still fall behind in answering questions regard
arXiv:2605.11612v1 Announce Type: new Abstract: Backdoor vulnerabilities widely exist in the fine-tuning of large language models(LLMs). Most backdoor poisoning methods operate mainly at the token lev
arXiv:2605.09515v1 Announce Type: new Abstract: Large language models rely on multihead attention, but interactions among heads remain poorly understood. We apply the Game Theoretic Free Energy Princi
arXiv:2605.09992v1 Announce Type: cross Abstract: Speculative decoding accelerates LLM inference by drafting future tokens with a small model, but drafter models degrade sharply under template perturb
arXiv:2510.20477v2 Announce Type: replace Abstract: Exploiting unlabeled data through semi-supervised learning (SSL) or leveraging pre-trained models via fine-tuning are two prevailing paradigms for a
arXiv:2605.10744v1 Announce Type: new Abstract: Safety-critical planning in complex environments, particularly at urban intersections, remains a fundamental challenge for autonomous driving. Existing
arXiv:2605.09693v1 Announce Type: cross Abstract: Yes. We find that large multimodal models develop mental imagery when solving spatial puzzles, and they do imagine sheep when solving sheep puzzles. W
arXiv:2605.09701v1 Announce Type: new Abstract: Existing latent world models for autonomous driving have opened a promising path toward future-aware driving intelligence. However, they typically treat
arXiv:2605.09603v1 Announce Type: new Abstract: Masked diffusion language models enable parallel token generation and offer improved decoding efficiency over autoregressive models. However, their perf
arXiv:2605.09773v1 Announce Type: cross Abstract: We use sparse autoencoder (SAE) feature steering to amplify Dark Triad personality traits (Machiavellianism, narcissism, and psychopathy) in Llama-3.3
arXiv:2605.08434v1 Announce Type: new Abstract: Vision-language-action (VLA) models provide a promising paradigm for scalable robotic manipulation, yet their reliance on success-only behavioral clonin
arXiv:2605.10439v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) has become a widely used mechanism for customizing diffusion models, enabling users to inject new visual concepts or styles t
arXiv:2603.16253v2 Announce Type: replace-cross Abstract: Vision-language process reward models (VL-PRMs) are increasingly used to score intermediate reasoning steps and rerank candidates under test-t
arXiv:2512.21815v2 Announce Type: replace Abstract: Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks. Entropy, as a measure of model uncertaint
arXiv:2605.08841v1 Announce Type: new Abstract: Vision-Language Models (VLMs) exhibit systematic bias toward visual illusions, recalling memorized facts rather than perceiving actual visual difference
arXiv:2605.08209v1 Announce Type: new Abstract: Deep learning methods are widely used under diverse resource constraints, resulting in models of varying sizes, such as the Vision Transformer (ViT) ser
arXiv:2510.08592v3 Announce Type: replace-cross Abstract: Test-Time Scaling (TTS) improves LLM reasoning by exploring multiple candidate responses and then operating over this set to find the best out
arXiv:2605.10002v1 Announce Type: new Abstract: Large vision-language models (VLMs) demonstrate strong performance in medical image understanding, but frequently generate clinically plausible yet inco
arXiv:2605.09606v1 Announce Type: cross Abstract: Recent advances in image-to-3D models have significantly improved the fidelity and accessibility of 3D content creation. Such a powerful reconstructio