Knowledge catalogue
arXiv:2605.29940v1 Announce Type: new Abstract: Large language models (LLMs) have been widely adopted for synthetic data generation, significantly reducing annotation costs. However, most existing stu
arXiv:2605.29795v1 Announce Type: new Abstract: Real-world tasks often lack large labeled datasets, motivating extensive work on learning in low-data regimes. However, existing approaches such as few-
arXiv:2605.29298v1 Announce Type: new Abstract: Bimanual coordination is essential for many real-world manipulation tasks, yet learning bimanual robot policies is limited by the scarcity of bimanual r
arXiv:2508.08677v2 Announce Type: replace-cross Abstract: Online Class-Incremental Learning (OCIL) enables models to learn continuously from non-i.i.d. data streams. Since samples of the data streams
My MLSys keynote on AI writing systems code got more interest than I expected. The recording will take a while, so in the finest tradition of AI labs sharing blog posts, we’re starting the Core Automa
arXiv:2505.02069v2 Announce Type: replace Abstract: We study the problem of neural logistic bandits, where the main task is to learn an unknown reward function within a logistic link function using a
arXiv:2605.30347v1 Announce Type: new Abstract: Data-driven approaches have revolutionized 3D vision, enabling transformers to effectively reconstruct and generate static 3D objects. However, generati
arXiv:2605.29812v1 Announce Type: new Abstract: Video Moment Retrieval (VMR) targets to retrieve the specific moment corresponding to a sentence query from an untrimmed video. Although recent works ha
arXiv:2511.08423v3 Announce Type: replace Abstract: A truly universal AI-Generated Image (AIGI) detector must simultaneously generalize across diverse generative models and varied semantic content. Cu
arXiv:2605.28839v1 Announce Type: new Abstract: Knowledge editing methods such as ROME and MEMIT update factual associations in transformer models by modifying MLP weights. While evaluated mainly by o
arXiv:2504.12512v2 Announce Type: replace Abstract: Mobile manipulation robots are continuously advancing, with their grasping capabilities rapidly progressing. However, there are still significant ga
arXiv:2605.28867v1 Announce Type: cross Abstract: Generating high-quality time-series data is challenging because real-world signals often exhibit multimodal patterns and multiscale dynamics, includin
This guide introduces torch.profiler, PyTorch's built-in profiling tool for analyzing model performance and identifying computational bottlenecks. It covers the basics of using the profiler to measure
arXiv:2605.28913v1 Announce Type: new Abstract: Large reasoning models (LRMs) often generate extensive chain-of-thought (CoT) traces before producing a final answer. As explicit textual artifacts, the
arXiv:2602.01456v2 Announce Type: replace-cross Abstract: Joint-Embedding Predictive Architectures (JEPA) learn view-invariant representations and admit projection-based distribution matching for coll
arXiv:2605.29122v1 Announce Type: new Abstract: It is often desirable to generalize medical imaging AI models trained with dense annotations to data acquired from different ultrasound scanners or clin
arXiv:2602.21565v2 Announce Type: replace Abstract: Generative Flow Networks (GFlowNets) learn to sample diverse candidates in proportion to a reward function, making them well-suited for scientific d
arXiv:2605.29098v1 Announce Type: new Abstract: Reconstructing object geometry from radio frequency (RF) signals is fundamentally challenging due to the lensless imaging nature of RF sensing, which le
arXiv:2605.24700v2 Announce Type: replace Abstract: Creating relightable urban scenes from images or videos is widely useful but highly ill-posed. Urban environments are typically unbounded and extend
arXiv:2605.29240v1 Announce Type: new Abstract: AI-augmented classrooms generate rich teacher and student feedback before graded outcomes become available, yet these signals can be difficult to transl
This Fireship video explores the forgotten developer or pivotal historical figure who played a critical role in saving or advancing the JavaScript language during a crucial period of its development.
There are still a few spots left for @hwchase17 + @traversal_ai founder @_anish_agarwal's technical fireside chat in NYC on June 2nd. Learn how Traversal builds, ships and improves their agents. Enjoy
arXiv:2605.28842v1 Announce Type: cross Abstract: The success of large language models (LLMs) across diverse NLP tasks has elevated the importance of reasoning chain optimization as a critical step in
Tip on Grok Build + Grok 4.3 VLM One of my critical tasks is to keep Grok VLM in the loop. Throwing a default system prompt usually yields poor results due to lack of context. Here is how to scale: -
arXiv:2605.29455v1 Announce Type: new Abstract: Multi-modal industrial anomaly detection typically relies on separate models for each product category, fundamentally limiting practical scalability. Wh
arXiv:2603.02082v2 Announce Type: replace Abstract: Children's acquisition of filler-gap dependencies has been argued by some to depend on innate grammatical knowledge, while others suggest that the d
arXiv:2603.23085v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) have enabled interpretable medical diagnosis by integrating visual perception with linguistic reasoning. Yet, existing
arXiv:2605.29548v1 Announce Type: new Abstract: Larger models learn tasks smaller models do not. What drives this phenomenon? We develop a simple phenomenological argument that power-law scaling alrea
arXiv:2508.15151v3 Announce Type: replace-cross Abstract: Computed tomography (CT) is important in clinical diagnosis, but acquiring high-resolution (HR) CT is constrained by radiation exposure risks.
arXiv:2602.10820v2 Announce Type: replace Abstract: A central requirement for the acceptance of machine learning methods for human-centric tasks is that they should be fair, in the sense that they sho
arXiv:2605.27668v1 Announce Type: cross Abstract: Probabilistic forecasting estimates the likelihood of uncertain future events. To improve LLM forecasting, existing methods typically learn from binar
arXiv:2511.15390v2 Announce Type: replace Abstract: Large language models (LLMs) have achieved remarkable performance on a wide range of tasks, hindering real-world deployment due to their massive siz
Banger paper from Harvard. AutoScientists drops the central planner entirely. Agents interpret shared experimental data, self-organize around promising directions, evaluate proposals before resource a
In this post, you learn how to build a custom portal with embedded SageMaker AI MLflow Apps UI. You walk through the architecture pattern behind a React front end paired with a Flask reverse proxy tha
arXiv:2605.27860v1 Announce Type: new Abstract: Retrieval-augmented generation combined with reinforcement learning has shown promise for grounding large language models in trustworthy medical evidenc
Canvas updates include: - Improved canvas interactions & more powerful tools - Better mobile experience - Image generation with GPT-Image 2, videos with Seedance, and animated SVGs - Updated visual ed
arXiv:2605.27449v1 Announce Type: cross Abstract: In the field of multimodal fact checking, the accuracy of retrieving evidence from different modalities has a significant impact on the downstream cla
arXiv:2605.28125v1 Announce Type: new Abstract: Many real-world 3D reconstruction applications demand photorealism and metric accuracy across unbounded, complex scenes with challenging lighting and im
arXiv:2602.12468v2 Announce Type: replace Abstract: Diffusion language models offer a promising alternative to autoregressive models due to their global, non-causal generation process, but their conti
arXiv:2605.27460v1 Announce Type: new Abstract: Single-frame atmospheric turbulence mitigation is inherently ill-posed due to spatially varying blur coupled with non-rigid geometric distortion. Existi
Vultr's data residency solution enables organizations to store and process data within specific geographic regions to meet regulatory compliance requirements such as GDPR, HIPAA, and local data protec
arXiv:2605.27931v1 Announce Type: new Abstract: Scientific diagrams are essential for communicating complex methodologies in academic papers. A natural way for researchers to specify such diagrams is
arXiv:2512.15791v2 Announce Type: replace-cross Abstract: In Artificial Intelligence (AI), language models have gained significant importance due to the widespread adoption of systems capable of simul
Fascinating results + Anthropic running away with it right now + So many people want to start their own company + Google over OpenAI + Vercel, Linear, Every, PostHog overperforming A great list if you
arXiv:2601.19302v3 Announce Type: replace Abstract: This paper introduces Formula Prompting (FP) and Formula-One Prompting (F-1), two single-call methods that elicit governing equations before solving
arXiv:2605.27944v1 Announce Type: new Abstract: With rapid advances in audio-visual generative models, reliable forgery detection becomes increasingly critical. Existing methods for audio-visual deepf
Fun fact: Australia is basically Scandinavia with the Sahara Desert bolted on. I LOVE this visualisation. Everyone imagines nature and the outback, but they don't realise just how urbanised we are. Cr
Managing planned maintenance is a critical part of running a reliable business. But as your cloud footprint grows into hundreds or even thousands of projects, keeping track of every individual update
ComfyUI is a node-based interface for Stable Diffusion that can be run on Windows using Docker and WSL2 (Windows Subsystem for Linux 2) for improved security and performance. This guide provides instr
arXiv:2504.10079v4 Announce Type: replace Abstract: Few-shot action recognition (FSAR) aims to recognize novel action categories with few exemplars. Existing methods typically learn frame-level repres
This post from Replit outlines a 4-step security framework for protecting vibecoded applications in production environments. It emphasizes that application speed must not come at the expense of securi
arXiv:2605.28802v1 Announce Type: new Abstract: Free-text explanations extend human label variation (HLV) beyond label disagreement by revealing the reasoning and preferences behind annotators' decisi
arXiv:2605.27523v1 Announce Type: cross Abstract: Deep generative models offer powerful tools for multivariate data analysis, but their black-box architectures are often unidentified and difficult to
arXiv:2501.01669v4 Announce Type: replace Abstract: Inverse reinforcement learning (IRL) has progressed significantly toward accurately learning the underlying rewards in both discrete and continuous
arXiv:2605.27546v1 Announce Type: new Abstract: Crisis Responders (CRs) rapidly assess thousands of youth SMS conversations each year to identify mental health concerns and guide support. Yet youth di
arXiv:2605.27734v1 Announce Type: new Abstract: Generative models, from diffusion models to large language models, achieve remarkable performance but at a cost in training data orders of magnitude lar
arXiv:2605.28462v1 Announce Type: new Abstract: Fast catching of free-flying objects is difficult because of short reaction time, impact uncertainty, and kinodynamic constraints. We use reinforcement
arXiv:2510.15839v2 Announce Type: replace Abstract: Random Utility Models (RUMs) are a classical framework for modeling user preferences and play a key role in reward modeling for Reinforcement Learni
arXiv:2605.28328v1 Announce Type: cross Abstract: When generating outputs for domains with specific validity constraints (e.g., a program should compile), LLMs often fail in a small number of focused
arXiv:2605.28309v1 Announce Type: new Abstract: In large-scale benchmarking of stochastic optimization algorithms, the key challenge is no longer whether repeated runs are needed for reliability, but