Knowledge catalogue
arXiv:2605.21765v1 Announce Type: new Abstract: The practical adoption of sampling-based inference (SAI) in Bayesian neural networks (BNNs) remains limited, partly due to persistent misconceptions abo
arXiv:2605.22715v1 Announce Type: cross Abstract: As wearable and mobile devices become increasingly embedded in daily life, they offer a practical way to continuously sense human motion in the wild.
arXiv:2605.22169v1 Announce Type: new Abstract: Deep learning models, including Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), have achieved state-of-the-art performance on vario
Validin, a data-intensive company, adopted Vultr's cloud infrastructure services to meet its high computational demands while achieving significant cost reductions of hundreds of thousands of dollars
arXiv:2601.23086v2 Announce Type: replace Abstract: Chain-of-thought (CoT) reasoning provides a significant performance uplift to LLMs by enabling planning, exploration, and deliberation of their acti
arXiv:2605.22679v1 Announce Type: new Abstract: Vision-language models learn powerful multimodal embeddings, yet their internal semantics remain opaque. While sparse autoencoders (SAEs) can extract in
arXiv:2605.22697v1 Announce Type: new Abstract: Robustness to domain changes is a key capability for effective deployment of human action recognition systems in real-world scenarios, where action cate
arXiv:2602.08028v1 Announce Type: cross Abstract: To address the instability of unguided reasoning paths in standard Chain-of-Thought prompting, recent methods guide large language models (LLMs) by fi
Gated DeltaNet-2 is almost exactly RWKV-7's DPLR recurrence, not acknowledging the elephant in the room 🙂 Gated DeltaNet-2 is here. 🚀 🔥 New paper: Gated DeltaNet-2: Decoupling Erase and Write in Linea
Harvard University just voted to limit the number of A grades given in undergraduate classes to about 20% of the class. I’m not in favor of this. It deeply runs counter to how I believe education shou
arXiv:2605.21379v2 Announce Type: cross Abstract: In The Algebraic Mind, Gary Marcus identified three components essential for any adequate cognitive architecture: operations over variables, recursive
arXiv:2602.03205v2 Announce Type: replace Abstract: While current humanoid whole-body control frameworks predominantly rely on the static environment assumptions, addressing tasks characterized by hig
Jeremy Howard argues that AI model developers at OpenAI and Anthropic should prioritize breaking backwards compatibility during the prototyping phase rather than maintaining it, suggesting that backwa
It’s a rough time to be a scientist. You spend decades learning how to measure things properly. How to separate signal from noise. How to distinguish hazard from risk. And then you open your phone and
Join @hwchase17 + @traversal_ai founder @_anish_agarwal for a technical fireside chat in NYC on June 2nd. Learn how Traversal builds, ships and improves their agents. Enjoy networking, drinks, and a l
arXiv:1607.06330v2 Announce Type: replace Abstract: In this doctoral thesis, we apply premises of cognitive linguistics to terminological definitions and present a proposal called the flexible termino
arXiv:2602.01760v2 Announce Type: replace Abstract: This paper focuses on a highly practical scenario: how to continue benefiting from the advantages of multi-modal image fusion under harsh conditions
arXiv:2605.20554v1 Announce Type: new Abstract: According to canonical negotiation theory, people's success in a negotiation depends on how well they balance competing demands--empathizing and asserti
arXiv:2605.22538v1 Announce Type: new Abstract: Traditional visual object tracking (VOT) methods typically rely on task-specific supervised training, limiting their generalization to unseen objects an
arXiv:2605.22098v1 Announce Type: new Abstract: The platonic representation hypothesis suggests that sufficiently large models converge to a shared representation geometry, even across modalities. Mot
arXiv:2605.22389v1 Announce Type: new Abstract: Effectively training Large Language Models (LLMs) for complex, long-CoT reasoning is often bottlenecked by the need for massive high-quality reasoning d
arXiv:2510.05094v2 Announce Type: replace Abstract: Recent video generation models can produce smooth and visually appealing clips, but they often struggle to synthesize complex dynamics with a cohere
Cognition AI announced the rollout of access to Windows virtual machines (VMs) for customers, with availability expanding over a 24-hour period. This feature likely enables users of Cognition's AI dev
arXiv:2605.20286v1 Announce Type: cross Abstract: Recent work has demonstrated the potential of contrastive steering for jailbreaking Large Language Models (LLMs). However, existing methods rely on li
arXiv:2605.21301v1 Announce Type: cross Abstract: In biomedical Subgroup Discovery, practitioners are interested in discovering interpretable and homogeneous subgroups within a group of patients. In t
arXiv:2502.06178v5 Announce Type: replace-cross Abstract: Bayesian optimization is highly effective for optimizing expensive-to-evaluate black-box functions, but it faces significant computational cha
In this post, we demonstrate how to build an AI-powered recruitment assistant using Amazon Bedrock that brings efficiencies to candidate evaluation, generates personalized interview questions, and pro
arXiv:2605.21029v1 Announce Type: new Abstract: Utilizing LLMs for automated taxonomy construction presents a clear opportunity for the comprehensive, yet efficient mapping of potentially complex doma
arXiv:2605.20529v1 Announce Type: new Abstract: In what ways might statistical signals in linguistic input assist with the acquisition of syntax? Here we hypothesize a mechanism called collocational b
arXiv:2510.06824v2 Announce Type: replace Abstract: To drive progress in science and engineering, large language models (LLMs) must be able to process large amounts of numerical data and solve long ca
Elon Musk just measured your existence by how many times your atoms have been inside a dying star. Musk: “How many times have your atoms been at the center of a star? I think it’s like on average thre
arXiv:2605.20199v1 Announce Type: new Abstract: We present FlowLM, a flow matching language model transformed from pre-trained diffusion language models via efficient fine-tuning. By re-aligning the c
For anyone who isn't sure, this is how you release a model and talk about the performance. Not 3-5 cherry-picked benchmarks. Performance：Qwen3.7-Max performs strongly across benchmarks in coding agent
AI service management has arrived, and the enterprises keeping pace didn’t wait for perfect conditions — they consolidated their data first. Of course, that urgency is creating an opening for companie
Gated DeltaNet-2 is here. 🚀 🔥 New paper: Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention Gated DeltaNet-2 outperforms KDA and Mamba-3, the latest and best recurrent architectures, hea
arXiv:2605.20600v1 Announce Type: new Abstract: Autoregressive (AR) visual generation has achieved remarkable performance but suffers from high memory usage and low throughput, as it requires caching
Learn how to design, calibrate, and run LLM-as-a-judge evaluators with fixed labels, human agreement checks, trace context, and Phoenix Evals. The post How to build LLM-as-a-Judge evaluators that hold
arXiv:2605.20827v1 Announce Type: new Abstract: Panoramic radiograph (PR) is fundamentally used in routine dental care, but it inherently provides only a two-dimensional (2D) projection of complex thr
I called my engineer friend at SpaceX the other day. 1am Pacific. 3am in Starbase. He was still in the office and not going home any time soon. And he was happy. Energized. Because he's directly influ
arXiv:2605.20285v1 Announce Type: new Abstract: We tackle the question of how to scale more efficiently across the many, ever-growing stages of current LLM training pipelines. Our guiding intuition st
arXiv:2605.21431v1 Announce Type: new Abstract: Video Virtual Try-On (VVT) aims to seamlessly replace a garment on a person in a video with a new one. While existing methods have made significant stri
arXiv:2605.20648v1 Announce Type: new Abstract: Learning from Demonstration (LfD) enables robots to learn complex behaviors from expert examples, yet existing approaches often fail to generalize to ne
arXiv:2605.20547v1 Announce Type: new Abstract: Many recent flow-matching and diffusion-style generative models rely on auxiliary stochastic dynamics during training: a richer process is simulated to
Learn how to build LLM Wikis and LLM Artifacts. New VIDEO: From LLM Wikis to LLM Artifacts Shared all my thoughts on why LLM wikis and HTML artifacts are a big deal. Plus, new tools to help you build
Replit Enterprise is a commercial offering from Replit designed for organizations and businesses seeking advanced collaborative coding and development capabilities on the Replit platform. This likely
arXiv:2601.22538v2 Announce Type: replace Abstract: Learning-to-defer (L2D) routes each decision to a system's own predictor or to an external expert. Streaming time-series settings break the offline-
arXiv:2605.21280v1 Announce Type: new Abstract: High-fidelity EEG generation is critical for alleviating data scarcity and addressing privacy constraints in large-scale neural modeling. Despite recent
LLM training is built on fast MatMuls. But many surrounding ops still run as memory-bound kernels. CODA reparameterizes them to hide in the matmul’s shadow, fused into its epilogue before results leav
arXiv:2605.20670v1 Announce Type: new Abstract: Looped Transformers (LT) have emerged as a powerful architecture by iterating their layers multiple times before decoding the final token. However, pair
arXiv:2605.21402v1 Announce Type: cross Abstract: Generative neural networks learn how to produce highly realistic images from a large, but finite number of examples - or do they simply memorise their
Nathan's @cursor_ai team didn't prompt-engineer their way to Composer 2.5. They trained it. The massive RL program runs RL rollouts on Fireworks, alongside production inference. 'Comment 🔥 to see my p
arXiv:2605.21388v1 Announce Type: new Abstract: Despite the remarkable empirical success of generative models, the available theory on their statistical accuracy in scientific computing remains largel
arXiv:2605.20751v1 Announce Type: new Abstract: Effective diabetes management requires continuous monitoring of glycemic levels. Clinically, glycemic control is assessed using metrics such as Time in
arXiv:2605.20195v1 Announce Type: new Abstract: A target-oriented proactive dialogue system is designed to steer conversations toward predefined targets while actively providing suggestions. The core
arXiv:2605.20404v1 Announce Type: new Abstract: The rapid adoption of Generative AI, including LLM-based chatbots like ChatGPT, has highlighted the need for accessible ways to support public understan
arXiv:2509.24725v3 Announce Type: replace Abstract: Estimating queue lengths at signalized intersections is a long-standing challenge in traffic management. Partial observability of vehicle flows comp
arXiv:2605.21300v1 Announce Type: new Abstract: Object hallucination is a significant challenge that hinders the application of large vision-language models (LVLMs) in practice. We hypothesize that on
Listen to the session or watch below AI companies want to build systems that understand the external world and overcome the limitations of LLMs. Recent developments have brought world models to the fo
arXiv:2605.20916v1 Announce Type: new Abstract: Implicit sentiment analysis is challenging because sentiment toward an aspect is often inferred from events rather than expressed through explicit opini
This isn't just corruption or grift, it's a full-on criminal enterprise. If Republicans in Congress hadn't sold themselves out completely, they'd shut this down immediately. Since the Trump administra