Knowledge catalogue
As artificial intelligence adoption accelerates inside enterprises, the economics of generative AI are forcing a fundamental rethink. Runaway token costs, data sovereignty demands and a growing gap be
arXiv:2602.16872v2 Announce Type: replace Abstract: Optical Character Recognition (OCR) is a fundamental task for digitizing information, serving as a critical bridge between visual data and textual u
arXiv:2605.27916v1 Announce Type: cross Abstract: The advancement of general medical Multimodal Large Language Models (MLLMs) has shown great potential for building conversational assistants to suppor
arXiv:2605.28037v1 Announce Type: new Abstract: Prompt-based personality control is a key technique for designing large language model (LLM) dialogue agents that behave consistently across social cont
arXiv:2605.27495v1 Announce Type: new Abstract: Data availability remains a critical bottleneck in many deep learning applications. Large-scale datasets are often expensive to collect, curate and anno
arXiv:2605.27813v1 Announce Type: cross Abstract: Text-to-image diffusion models generate images through an iterative denoising process, so internal neural layers produce trajectories of activations r
arXiv:2605.28123v1 Announce Type: new Abstract: Prompt-based verification is widely used to mitigate hallucinations in large vision-language models (LVLMs), yet when it helps remains poorly understood
arXiv:2605.28338v1 Announce Type: new Abstract: Large language models(LLMs) increasingly match expert performance on licensing examinations, yet routine clinical use remains limited because governance
arXiv:2605.27947v1 Announce Type: new Abstract: World Action Models (WAMs) improve robot manipulation by using video-based future representations to condition action generation. In pixel-space WAMs, h
arXiv:2602.04898v3 Announce Type: replace-cross Abstract: Text-to-image (T2I) diffusion models are widely adopted for their strong generative capabilities, yet remain vulnerable to backdoor attacks. E
arXiv:2510.20665v3 Announce Type: replace Abstract: Evaluating the quality of reasoning traces from large language models remains understudied, labor-intensive, and unreliable: current practice relies
today is (potentially) a great day for the GPU poors if DiffusionBlocks works on fine-tuning existing models, then literally any reasonable consumer GPU can do LLM fine-tuning will make a video on thi
arXiv:2512.14561v2 Announce Type: replace Abstract: Despite the growing promise of large language models (LLMs) in automated essay scoring (AES), empirical findings regarding their reliability compare
arXiv:2605.26683v1 Announce Type: cross Abstract: Cross-lingual transfer in language models is difficult to study in natural corpora because lexical overlap, morphology, data imbalance, and tokenizati
arXiv:2605.26440v1 Announce Type: new Abstract: The rapid advancement of Large Language Models (LLMs) has outpaced the scalability of traditional evaluation benchmarks, which remain heavily dependent
arXiv:2605.26949v1 Announce Type: new Abstract: 3D shape completion from partial scans remains challenging for unseen categories and noisy real-world observations, where geometry alone is often insuff
arXiv:2605.27236v1 Announce Type: new Abstract: Continuous and global detection of large methane emissions is a crucial step for global warming mitigation. Satellite observations, such as from S5P/TRO
arXiv:2605.26947v1 Announce Type: new Abstract: Kazakh is underrepresented in resources for evaluating the safety behavior of large language models. We present KZ-SafetyPrompts, a Kazakh prompt datase
arXiv:2605.26992v1 Announce Type: new Abstract: Vision-language models (VLMs) may memorize undesirable information from training data, motivating growing interest in machine unlearning. In this work,
arXiv:2605.26632v1 Announce Type: new Abstract: Diffusion Transformers (DiT) achieve strong performance in image generation but incur substantial inference costs. While prior work has reduced this cos
arXiv:2605.26733v1 Announce Type: cross Abstract: Looped Language Models (LoopLMs) enable efficient latent reasoning through depth recurrence, yet exhibit unreliable test-time scaling behavior: perfor
arXiv:2601.07085v2 Announce Type: replace-cross Abstract: Large language model (LLM)-based conversational AI systems present a challenge to human cognition that current frameworks for understanding mi
The best research labs are building what comes after static models. Congrats to @trajectorylabs on the launch! Excited to have them training on the AI Native Cloud as they push the frontier on Continu
arXiv:2605.26670v1 Announce Type: cross Abstract: Sequential editing of structured knowledge in large language models allows targeted factual updates without retraining, yet existing methods often rel
The open source community has been delivering on LTX 2.3 LoRAs. Fine tuning LTX 2.3 unlocks control that you can't get from closed models. Here are 7 LoRAs that can save your footage. There are too ma
arXiv:2605.26161v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) are increasingly pretrained on large corpora, raising concerns that evaluation datasets may have been exposed du
arXiv:2605.26013v1 Announce Type: cross Abstract: We introduce AdvantageFlow, a forward-process reinforcement learning algorithm for rectified flow models. Unlike Flow-GRPO, which optimizes the revers
arXiv:2605.25230v1 Announce Type: new Abstract: Recent work on recursive architectures has shown that tiny neural networks can be surprisingly powerful on structured reasoning tasks. The trick is to m
arXiv:2601.21406v3 Announce Type: replace-cross Abstract: Unified Multimodal Models (UMMs) integrate both visual understanding and generation within a single framework. Their ultimate aspiration is to
arXiv:2605.25443v1 Announce Type: new Abstract: Post-training has significantly enhanced the reasoning capability of Large Reasoning Models (LRMs), especially with Reinforcement Learning (RL) like Gro
arXiv:2605.24140v1 Announce Type: new Abstract: Multi-step reasoning remains a central challenge for large language models: single-pass generation is efficient but lacks accuracy; tree-search methods
Infinite context windows seem to present a very large problem to using AI. Today's models already leak too much old information into current responses, a distraction that is part of why they are cogni
arXiv:2602.02839v3 Announce Type: replace Abstract: Enabling robots to perform novel manipulation tasks from natural language instructions remains a fundamental challenge in robotics, despite signific
arXiv:2605.25179v1 Announce Type: new Abstract: Audio-language models (ALMs) are increasingly used for audio captioning, question answering, and open-ended audio understanding, but their inference cos
arXiv:2506.09084v2 Announce Type: replace-cross Abstract: Whole-page optimization (WPO) decides how search and recommendation results are surfaced to users, and large language models (LLMs) open a new
arXiv:2602.02544v2 Announce Type: replace-cross Abstract: While Diffusion Language Models (DLMs) offer a flexible, arbitrary-order alternative to the autoregressive paradigm, their non-causal nature p
arXiv:2605.24477v1 Announce Type: new Abstract: The Normalized Maximum Likelihood (NML) codelength, or stochastic complexity, represents a principled criterion for universal coding. While recent coare
arXiv:2605.25566v1 Announce Type: new Abstract: Clinical decision-making requires reasoning over incomplete, imprecise, and linguistically expressed patient narratives. While large language models (LL
arXiv:2502.07646v3 Announce Type: replace Abstract: Causal additive models provide a tractable yet expressive framework for causal discovery in the presence of hidden variables. When unobserved backdo
arXiv:2509.06858v2 Announce Type: replace-cross Abstract: Large Language Models are increasingly used to simulate human opinion dynamics, yet the effect of genuine interaction is often obscured by sys
arXiv:2605.23039v1 Announce Type: cross Abstract: How do learners acquire knowledge of what is unacceptable without negative evidence? Construction Grammar proposes statistical preemption: exposure to
arXiv:2605.23189v1 Announce Type: new Abstract: Conformal prediction (CP) gives distribution-free coverage for modern vision and language models, but it is often forced to make a ranking decision from
arXiv:2603.07079v2 Announce Type: replace-cross Abstract: On-policy distillation is a promising approach for transferring knowledge between language models, where a student learns from dense token-lev
arXiv:2603.19167v2 Announce Type: replace Abstract: We evaluate Large Language Models (LLMs) in repeated game-theoretic settings to assess whether strategic performance reflects genuine reasoning or r
arXiv:2602.18176v3 Announce Type: replace Abstract: Masked Diffusion Models (MDMs) enable flexible decoding orders, yet existing samplers remain largely greedy, selecting locally certain tokens withou
arXiv:2605.23145v1 Announce Type: cross Abstract: Individual fairness, the notion that 'similar individuals should be treated similarly,' provides a strong and flexible fairness guarantee for algorith
arXiv:2605.22836v1 Announce Type: cross Abstract: Rapid earthquake magnitude estimation is crucial for effective early warning systems that can save lives and reduce economic damage. In this paper, we
arXiv:2605.23194v1 Announce Type: cross Abstract: Fast and reliable optimal power flow (OPF) approximation is essential for reliable smart-grid operation, yet many learning-based surrogates either fla
arXiv:2601.00969v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models provide strong action priors for robotic manipulation, but their reactive behavior can fail under distribu
We built Aleph as one of the first generalist text-based editing models. Aleph 2.0 takes it further: visual prompting for precise control, longer videos (up to 30 seconds), and yes, multi-shot support
> I’m now in the LeCun/Marcus camp on LLMs > real programming agents will need world models > not some RLVR shit it’s over The Eternal Sloptember https://geohot.github.io//blog/jekyll/update/2026/05/2
arXiv:2605.22222v1 Announce Type: new Abstract: Partial differential equation (PDE) foundation models are pretrained networks that forecast how physical fields like velocity and pressure evolve from a
arXiv:2603.02938v2 Announce Type: replace Abstract: Graph-based tasks in the zero-shot setting remain a significant challenge due to data scarcity and the inability of traditional Graph Neural Network
arXiv:2605.21846v1 Announce Type: cross Abstract: Causal discovery from multivariate time series is challenging when causal effects may occur both across time and within the same sampling interval. Th
arXiv:2605.22774v1 Announce Type: new Abstract: Real-time cognitive load assessment is essential for adaptive human-computer interaction but remains challenging due to limited labeled data and poor cr
arXiv:2605.21539v1 Announce Type: new Abstract: We propose DualOptim+, a novel optimization framework for improving machine unlearning in large language models. It introduces a base state to capture c
Image diffusion models like Flux natively output at 1k resolution, but what if we want to generate much higher resolution images (6k+)? SEGA modifies the RoPE encodings during the diffusion process to
arXiv:2601.05157v2 Announce Type: replace-cross Abstract: In this work, we give a {rm poly}(d,k) time and sample algorithm for efficiently learning the parameters of a mixture of k spherical distribut
arXiv:2605.21911v1 Announce Type: new Abstract: We develop a principled framework for analyzing and designing noise schedules in diffusion models. We show that one can recast this design problem as an
This article describes techniques for using prompt caching to improve the inference speed and efficiency of open-source large language models when deployed on Databricks' platform. Prompt caching redu