Knowledge catalogue
arXiv:2412.13050v2 Announce Type: replace-cross Abstract: In this paper, we introduce Modality-Inconsistent Continual Learning (MICL), a new continual learning scenario for Multimodal Large Language M
more demos on Interaction Models collaboratively doing system design, reading papers, fact-checking with live generative UI 1. (System design) - The Interaction Models see your screen and collaborates
arXiv:2605.11290v1 Announce Type: new Abstract: Capability distillation applies knowledge distillation to selected model capabilities, aiming to compress a large language model (LLM) into a smaller on
arXiv:2605.12384v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable capabilities, but they still frequently produce hallucinations. These hallucinations are diffi
arXiv:2304.10891v2 Announce Type: replace-cross Abstract: Transformer-based models are becoming a central paradigm in autonomous driving because they can capture long-range spatial dependencies, multi
We’re training models wrong and it’s due to chatGPT. Even the modern coding agents used daily still use message-based exchanges: They send messages to users, to themselves (CoT) and to tools, and rece
arXiv:2605.10075v1 Announce Type: new Abstract: Large language models (LLMs) require reliable evaluation from pre-training to test-time scaling, making evaluation a recurring rather than one-off cost.
arXiv:2605.10819v1 Announce Type: cross Abstract: Vision-language-action (VLA) models remain constrained by the scarcity of action-labeled robot data, whereas action-free videos provide abundant evide
arXiv:2512.03706v2 Announce Type: replace-cross Abstract: Coarse graining (CG) is an important task for efficient modeling and simulation of complex multi-scale systems, such as the conformational dyn
arXiv:2605.08249v1 Announce Type: new Abstract: Frozen vision foundation models do not merely extract features; they organize images through a learned coordinate system. We ask whether that coordinate
arXiv:2605.10198v1 Announce Type: cross Abstract: Erasing specific concepts from text-to-image diffusion models is essential for avoiding the generation of copyrighted and explicit content. Closed-for
arXiv:2605.08195v1 Announce Type: new Abstract: Local execution of AI on edge devices is important for low latency and offline operation. However, deploying models on diverse hardware remains fragment
arXiv:2605.09081v1 Announce Type: cross Abstract: We introduce the first universal pretraining corpus for industrial time-series data: FactoryNet. 51M datapoints across 23k end-to-end task executions
arXiv:2605.09949v1 Announce Type: new Abstract: Understanding how chemical language models (CLMs) learn chemical meaning from molecular string representations, rather than only surface-level string pa
arXiv:2605.09718v1 Announce Type: cross Abstract: Many systems in physics, engineering, and biology exhibit multiscale stochastic dynamics, where low-dimensional slow variables evolve under the influe
arXiv:2605.10886v1 Announce Type: cross Abstract: Recent GPU generations deliver significantly higher FLOPs using lower-precision arithmetic, such as FP8. While successfully applied to large language
arXiv:2605.08094v1 Announce Type: cross Abstract: Accurate clinical diagnosis requires extensive domain knowledge and complex clinical reasoning capabilities. Although large language models (LLMs) hol
arXiv:2605.09503v1 Announce Type: new Abstract: Large-scale visual generative models have achieved remarkable performance. However, their high computational and memory costs make deployment challengin
arXiv:2605.09666v1 Announce Type: cross Abstract: Multiple Sclerosis (MS) is a chronic autoimmune disease that can significantly reduce the quality of life of a patient. Existing treatment options can
arXiv:2602.00986v2 Announce Type: replace Abstract: Recent studies show that LLM hidden states encode reward-related information, such as answer correctness and model confidence. However, existing app
arXiv:2601.20756v2 Announce Type: replace Abstract: Score-based diffusion models have recently been extended to infinite-dimensional function spaces, with uses such as inverse problems arising from pa
arXiv:2605.08241v1 Announce Type: cross Abstract: Self-supervised learning (SSL) has transformed representation learning for large models, yet remains unexplored for microcontroller (MCU)-class models
arXiv:2605.09965v1 Announce Type: new Abstract: The real world unfolds along a single set of physics laws, yet human intelligence demonstrates a remarkable capacity to generalize experiences from this
arXiv:2605.08128v1 Announce Type: cross Abstract: Gene Regulatory Network (GRN) inference is essential for understanding complex cellular mechanisms, rendered tractable through single-cell transcripto
arXiv:2605.09125v1 Announce Type: cross Abstract: Preliminary low-thrust spacecraft mission design is a global search problem characterized by a complex solution landscape, multiple objectives, and nu
We published new research on how we serve post-trained Qwen3 235B models on NVIDIA GB200 NVL72 Blackwell racks. GB200 is a major step up over Hopper for high-throughput inference on large MoE models,
arXiv:2510.03761v2 Announce Type: replace-cross Abstract: The widespread use of preprint repositories such as arXiv has accelerated the communication of scientific results but also introduced overlook
arXiv:2605.06829v1 Announce Type: cross Abstract: We survey continuous-time generative modeling methods based on transporting a simple reference distribution to a data distribution via stochastic or d
Dealing with quirks introduced by switching models doesn't have to be hard -- we recently introduced a 'harness profile' API in Deep Agents as a solution. Profiles adjust system prompts, tool descript
arXiv:2605.07210v1 Announce Type: cross Abstract: PromptReps showed that an autoregressive language model can be used directly as a retriever by prompting it to generate dense and sparse representatio
arXiv:2605.07844v1 Announce Type: new Abstract: Energy-based learning is a powerful framework for generative modelling, but its training is inherently non-convex, leading potentially to sensitivity to
arXiv:2602.20338v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) prompting significantly improves reasoning in Large Language Models, yet the temporal dynamics of the underlying representati
arXiv:2512.20974v3 Announce Type: replace-cross Abstract: Bayesian Reinforcement Learning (BRL), a subclass of Meta-Reinforcement Learning (Meta-RL), provides a principled framework for generalisation
arXiv:2508.05803v2 Announce Type: replace Abstract: Human memory is fleeting. As words are processed, the exact wordforms that make up incoming sentences are rapidly lost. Cognitive scientists have lo
arXiv:2605.07514v1 Announce Type: cross Abstract: World Action Models (WAMs) enable decision-making through imagined rollouts by predicting future observations and actions. However, the reliability of
arXiv:2605.07640v1 Announce Type: cross Abstract: Remote sensing lithology interpretation is fundamental to geological surveys, mineral exploration, and regional geological mapping. Unlike general lan
arXiv:2601.04731v2 Announce Type: replace Abstract: Current critic-free RL methods for large reasoning models suffer from severe inefficiency when training on positive homogeneous prompts (where all r
arXiv:2605.07201v1 Announce Type: cross Abstract: This paper describes our system for the EEUCA 2026 Shared Task on Understanding Toxic Behavior in Gaming Communities. The task involves classifying Wo
arXiv:2605.06298v2 Announce Type: replace-cross Abstract: Training world models on vast quantities of unlabelled videos is a critical step toward fully autonomous intelligence. However, the prevailing
arXiv:2601.14958v3 Announce Type: replace-cross Abstract: The performance of Language Models (LMs) on low-resource, morphologically rich languages like Sinhala remains largely unexplored, particularly
arXiv:2603.23198v2 Announce Type: replace-cross Abstract: Scaling autoregressive large language models (LLMs) has driven unprecedented progress but comes with vast computational costs. In this work, w
This seems like a critical reason to open up about AI use in academia. Scholars are using old AI models, badly, and not talking about it. New models hallucinate very few citations, and good agentic ha
ai coding is getting expensive use more open models! Kimi K2.6 on @baseten is ~5x cheaper than Opus 4.7 For a large majority of tasks, it's roughly the same performance If you want to use open models
arXiv:2603.00492v2 Announce Type: replace Abstract: Per-scene optimization methods such as 3D Gaussian Splatting provide state-of-the-art novel view synthesis quality but extrapolate poorly to under-o
arXiv:2605.04555v1 Announce Type: new Abstract: Model-based reinforcement learning (MBRL) offers a promising approach for data-efficient energy management in buildings, combining the strengths of pred
arXiv:2605.05025v1 Announce Type: new Abstract: We propose a lightweight and single-pass uncertainty quantification method for detecting hallucinations in Large Language Models. The method uses attent
arXiv:2605.04678v1 Announce Type: cross Abstract: Latent actions serve as an intermediate representation that enables consistent modeling of vision-language-action (VLA) models across heterogeneous da
arXiv:2605.05197v1 Announce Type: new Abstract: Grammaticality and likelihood are distinct notions in human language. Pretrained language models (LMs), which are probabilistic models of language fitte
arXiv:2605.04063v1 Announce Type: new Abstract: Alzheimer's Dementia (AD) is a progressive neurodegenerative disease marked by irreversible decline, making reliable modeling of its progression essenti
arXiv:2605.04344v1 Announce Type: cross Abstract: We introduce a simple yet powerful framework for training large language models. In contrast to the standard autoregressive next-token prediction base
arXiv:2502.12370v3 Announce Type: replace Abstract: Recent advancements in transformer-based models have greatly improved time series analysis, providing robust solutions for tasks such as forecasting
arXiv:2605.03546v1 Announce Type: cross Abstract: Turning ideas into full software projects from scratch has become a popular use case for language models. Agents are being deployed to seed, maintain,
arXiv:2605.05093v1 Announce Type: cross Abstract: Regularization is often used in high-dimensional regression settings to generate a sparse model, which can save tremendous computing resources and ide
arXiv:2605.04494v1 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) has been popular for aligning text-to-image (T2I) diffusion models with human preferences. As a main
arXiv:2601.21851v2 Announce Type: replace Abstract: Foundation models, despite their robust zero-shot capabilities, remain vulnerable to spurious correlations and 'Clever Hans' strategies. Existing mi
arXiv:2605.00968v1 Announce Type: cross Abstract: Positional encoding plays a pivotal role in determin?ing the extrapolation and generalization performance of wireless foundation models for channel st
arXiv:2509.20789v4 Announce Type: replace Abstract: The remarkable success of modern AI has been closely tied to scaling laws, yet the finite supply of high-quality data makes data efficiency--learnin
arXiv:2605.02906v1 Announce Type: new Abstract: In the field of software operations, Large Language Models (LLMs) have attracted increasing attention. However, existing research has not yet achieved e
arXiv:2605.03111v1 Announce Type: cross Abstract: Social-educational robots designed for socially interactive pedagogical support, such as the Robot Study Companion (RSC), rely on responsive, privacy-
arXiv:2605.01555v1 Announce Type: new Abstract: We introduce an autonomous multiagent framework for mechanistic interpretability that automates both explaining and finding internal features in large l