Knowledge catalogue
TESSERA leverages Vultr’s cloud GPU infrastructure, specifically AMD Instinct™ GPUs, to process satellite data at planetary scale. By integrating foundation‑model AI, TESSERA accelerates Earth‑observa
OpenAI admitted that an agent powered by its GPT‑5.6 Sol and a pre‑release model escaped a sandboxed test environment and gained unauthorized access to Hugging Face’s servers while attempting to solve
A federal judge has signed off on Anthropic's 1.5 billion class action settlement with authors who accused the company of training its AI models on copyrighted books, as reported earlier by Reuters. I
AI has entered the gigascale era. The world’s most advanced AI factories are bringing together hundreds of thousands of GPUs and CPUs to train frontier models, power agentic AI and generate intelligen
I've been building an AI that learns to play the classic Snake game through reinforcement learning. The goal is to reach high scores while keeping training time as low as possible. The current version
The NVIDIA GB300 NVL72 platform set a world record by delivering 1,648 TFLOPs per GPU during the pre‑training of DeepSeek‑V3 671B, a mixture‑of‑experts (MoE) model. This achievement leveraged fifth‑ge
Gizmo is a simulation-authoring agent that converts textual descriptions and reference images into structured, editable 3D scenes tailored for robotics workflows. It was publicly released as a beta on
this is important and true. and if you don’t understand it you don’t really understand what’s going on. @GaryMarcus Yes — model makers quietly went from benchmarking LLMs to benchmarking LLM+harness,
Vibe coding isn't just for your PC anymore. Here's LLM Hub generating and previewing code entirely on an iPhone. Everything runs locally. Using the RunAnywhere SDK, Timmy Qian ported LLM Hub, an Andro
We had guessed reward seeking might increase over the course of capabilities-focused RL training, but had no way of measuring it until now. We’re continuing to collaborate with Apollo Research to impr
// Global Workspace in LLMs // arXiv paper for the popular J-space work from Anthropic. (bookmark it) The short recap: If you build on chain-of-thought or steering vectors, this work provides a mechan
arXiv:2603.21393v2 Announce Type: replace Abstract: The widespread use of AI and ML models in sensitive areas raises significant concerns about fairness. While the research community has introduced va
arXiv:2607.13237v1 Announce Type: new Abstract: Precise spatial-temporal annotation of laparoscopic videos is time-consuming and requires expert knowledge. We propose a human-in-the-loop knowledge acq
arXiv:2607.13205v1 Announce Type: cross Abstract: Attention-based KV cache eviction (H2O and its descendants) compresses the memory-constrained state of a long-context model by ranking tokens on accum
arXiv:2607.13453v1 Announce Type: cross Abstract: Artificial Intelligence (AI), especially Generative AI (GenAI), adoption has increased in industries significantly in recent years. However, the use o
arXiv:2607.13250v1 Announce Type: new Abstract: We present extbf{AffectFlow-DINO}, a multi-task learning system for the 11th ABAW challenge that extends a standard deterministic architecture with a co
arXiv:2607.13094v1 Announce Type: cross Abstract: The rise of Artificial Intelligence (AI) enables automatic analysis of large amounts of data. Previously time-consuming and labor-intensive tasks can
arXiv:2607.13437v1 Announce Type: new Abstract: Recent vision models such as CLIP and SAM enable training-free segmentation and semantic encoding for fine-grained classification. A common approach is
arXiv:2607.13703v1 Announce Type: new Abstract: We investigate conditional invertible neural networks (cINNs) as probabilistic inverse-dynamics models for multirotor control. For a planar X8 coaxial m
arXiv:2603.12712v2 Announce Type: replace-cross Abstract: Large language models~(LLMs) have demonstrated remarkable capabilities in code generation, yet their performance remains limited on domain-spe
arXiv:2607.13241v1 Announce Type: cross Abstract: Traffic forecasting is highly challenging due to complex and nonlinear spatial and temporal dependencies. Self-attention mechanisms have been widely a
arXiv:2607.13884v1 Announce Type: new Abstract: Large Language Model (LLM) agents have shown remarkable capabilities in autonomous decision-making by generating sequential trajectories of states, acti
arXiv:2607.13498v1 Announce Type: new Abstract: Learning a compact model of the world from interaction data is central to sample-efficient deep reinforcement learning. Spectral representation methods
arXiv:2607.13095v1 Announce Type: cross Abstract: We present a full-pipeline inference optimization for the MiMo-V2.5 model family, which combines Hybrid Sliding Window Attention (Hybrid SWA), sparse
arXiv:2607.13429v1 Announce Type: cross Abstract: Finetuning a pretrained vision-language model (VLM) on robot demonstrations via behavior cloning (BC) has become the standard recipe for vision-langua
arXiv:2607.13218v1 Announce Type: cross Abstract: In this work, we study various graph partitioning problems under a general demand model. In each such task, we are given a graph G=(V,E,c,w) with a ca
arXiv:2607.13712v1 Announce Type: cross Abstract: Despite the rapid progress of Multimodal Large Language Models (MLLMs), they still suffer from untruthfulness issues, such as visual hallucinations, c
arXiv:2607.13646v1 Announce Type: cross Abstract: Recent advances in 3D human reconstruction have improved overall performance, yet current models still fail in the most challenging real-world scenari
arXiv:2607.13501v1 Announce Type: new Abstract: Reinforcement learning for multi-turn search reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and har
arXiv:2601.12349v3 Announce Type: replace-cross Abstract: Large multimodal model powered GUI agents are emerging as high-privilege operators on mobile platforms, entrusted to perceive screen content a
arXiv:2607.13415v1 Announce Type: new Abstract: Recent advances in generative models and technological innovations have significantly addressed the fundamental challenges of character image animation.
arXiv:2505.18231v3 Announce Type: replace-cross Abstract: Large Language Model (LLM) inference is typically memory-intensive, especially when processing large batch sizes and long sequences, due to th
arXiv:2603.22372v3 Announce Type: replace-cross Abstract: Recent advances in multimodal learning have motivated the integration of auxiliary modalities such as text or vision into time series (TS) for
arXiv:2508.16403v3 Announce Type: replace Abstract: Accurately predicting the performance of active radio frequency (RF) circuits is essential for modern wireless systems but remains challenging due t
arXiv:2607.13323v1 Announce Type: new Abstract: The Segment Anything Model (SAM) has demonstrated strong generalizability across a variety of segmentation tasks. However, SAM often struggles in situat
arXiv:2607.13124v1 Announce Type: cross Abstract: Structured pruning is a hardware-friendly way to compress LLMs, but it is mostly validated on multiple-choice recognition tasks, while the same compre
arXiv:2510.01943v3 Announce Type: replace-cross Abstract: Quasar-convex functions form a broad nonconvex class with applications to linear dynamical systems, generalized linear models, and Riemannian
arXiv:2607.13768v1 Announce Type: new Abstract: Collisions of rigid-link robots and rigid environments are often modeled as instantaneous events. Under this idealization, the impact forces become impu
arXiv:2607.13539v1 Announce Type: new Abstract: While traditional graphics methods often synthesize 3D indoor scenes autoregressively or hierarchically, recent vision-language model (VLM)-based genera
arXiv:2607.13174v1 Announce Type: cross Abstract: Multimaterial 3D printing enables the fabrication of functionally graded components, but optimizing their spatial material distribution alongside stru
arXiv:2607.13565v1 Announce Type: cross Abstract: We investigate which language model evasion attacks survive state-of-the-art adversarial fine-tuning, developing strategies that sweep the top 5 posit
arXiv:2607.13541v1 Announce Type: cross Abstract: To overcome data scarcity and privacy constraints in data collection, it has become standard practice across academia and industry to augment real tra
arXiv:2607.11987v1 Announce Type: new Abstract: Perineural invasion (PNI) is associated with poor postoperative outcomes in intrahepatic cholangiocarcinoma, but it is confirmed by surgical pathology.
arXiv:2511.23276v2 Announce Type: replace Abstract: Effective HFMD surveillance requires forecasts capturing both time-series patterns and contextual drivers such as school calendars, weather, and pol
arXiv:2607.11949v1 Announce Type: cross Abstract: We present a clinically deployed end-to-end auto-contouring system for cervical cancer radiotherapy planning, anchored by the Boundary-Aware Transform
arXiv:2607.11967v1 Announce Type: cross Abstract: Independently trained neural networks have no shared neuron-index reference frame, so comparing them requires accounting for coordinate freedom. Neura
arXiv:2607.12723v1 Announce Type: cross Abstract: Filesystem isolation in container ecosystems is often weakened by cross-boundary path misresolution, causing path traversal (PaTra) vulnerabilities. T
Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external knowledge but still suffers from long contexts and disjoint retrieval–generation optimization. In this work, we
arXiv:2507.21245v2 Announce Type: replace-cross Abstract: An accurate initial heading angle is essential for efficient and safe navigation across diverse domains. Unlike magnetometers, gyroscopes can
arXiv:2607.12185v1 Announce Type: new Abstract: Embodied accounts of semantic memory highlight the role of sensorimotor systems in acquiring and storing knowledge. Congenitally blind populations offer
arXiv:2607.12764v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) has emerged as a critical paradigm for grounding Multimodal Large Language Models (MLLMs) in external knowledge. Re
arXiv:2607.12455v1 Announce Type: new Abstract: Quantitative strategy optimization remains largely manual, requiring domain experts to identify weak signals, tune risk-control rules, and repeatedly va
arXiv:2607.11956v1 Announce Type: cross Abstract: Data Shapley is the standard principled answer to which training points are worth what, and its k-nearest-neighbor (KNN) specialization is the version
arXiv:2607.11464v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) addresses the limitations of Large Language Models (LLMs) when providing responses to domain-specific questions.
arXiv:2607.11588v2 Announce Type: replace Abstract: We present FoundationGeo, a two-stage framework that explicitly bridges relative and metric prediction via spatial calibration and principled data d
arXiv:2606.20751v2 Announce Type: replace Abstract: Advanced Air Mobility (AAM) is an emerging low-altitude transportation system whose successful deployment depends on both technological progress and
arXiv:2604.10925v2 Announce Type: cross Abstract: Natural language remains the predominant way people interact with large language models (LLMs). However, users often struggle to precisely express and
arXiv:2607.12752v1 Announce Type: cross Abstract: While recent advances in 3D generation have enabled impressive visual synthesis, existing methods often rely on 2D diffusion supervision without expli
I’m very excited by this test time training work for robotic learning! It’s an awesome collaboration between @StanfordSVL and @NVIDIARobotics ! We scaled a robot model natively to 8,000 timesteps of c
arXiv:2607.11656v2 Announce Type: replace-cross Abstract: Accurate diagnostic classification and disease-severity prediction for Alzheimer's disease are hampered by the incompleteness and heterogeneit