Knowledge catalogue
arXiv:2607.07608v1 Announce Type: cross Abstract: Mainstream Vision-Language-Action (VLA) models predict actions primarily from the current observation under a Markovian assumption, thus struggling wi
arXiv:2603.19742v2 Announce Type: replace-cross Abstract: Understanding the internal mechanisms of transformer-based large language models (LLMs) is crucial for their reliable deployment and effective
arXiv:2606.15346v2 Announce Type: replace Abstract: Spatio-temporal prediction supports radar/satellite nowcasting and city-scale traffic monitoring, but modern models are often too expensive for real
arXiv:2607.06631v1 Announce Type: cross Abstract: Video Diffusion Models (VDMs) have demonstrated superior generation quality but suffer from prohibitive computational costs. While recent few-step dis
arXiv:2607.06896v1 Announce Type: cross Abstract: Robust dynamic object detection and tracking are essential for enabling robots to operate safely and effectively alongside humans in complex environme
arXiv:2607.07683v1 Announce Type: new Abstract: Electrocardiography (ECG) is one of the most widely used tests for diagnosing cardiovascular disease. Yet several remote clinics still utilize paper ECG
arXiv:2508.21556v3 Announce Type: replace Abstract: Modeling human-object interactions (HOI) from an egocentric perspective is a critical yet challenging task, particularly when relying on sparse sign
arXiv:2607.06982v1 Announce Type: new Abstract: Convolutional neural networks (CNNs) have demonstrated encouraging results in image classification tasks. However, the prohibitive computational cost of
arXiv:2607.07187v1 Announce Type: new Abstract: Local editing of 3D objects remains a long-standing challenge. When interacting with 3D content, humans naturally tend to specify a coarse region of int
arXiv:2603.21489v2 Announce Type: replace-cross Abstract: AI agents have become increasingly capable at isolated software engineering (SWE) tasks such as resolving issues on Github. Yet long-horizon t
arXiv:2607.06776v1 Announce Type: new Abstract: We introduce an efficient Bayesian deep ensemble method for predictive regression designed to enhance interpretability while maintaining competitive pre
arXiv:2607.06772v1 Announce Type: new Abstract: Learned optimization aims to improve upon hand-designed optimizers (e.g., Adam and Muon) by meta-learning small neural network optimizers over a distrib
arXiv:2607.07001v1 Announce Type: new Abstract: Anticipating human motion from an egocentric perspective is fundamental for proactive assistance in AR/VR, human-robot collaboration, and embodied AI. W
arXiv:2607.07459v1 Announce Type: cross Abstract: We present EmbodiedGen V2, a generative 3D world engine for building executable sim-ready environments for embodied intelligence. Sim-ready 3D asset g
arXiv:2602.23802v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have shown remarkable progress in visual reasoning and understanding tasks but still struggle to capture th
Emad Mostaque appeared as a guest on The Beyond Tomorrow Podcast, with the episode released as a YouTube premiere where he engaged with viewers in the chat. The post promotes the episode availability
arXiv:2607.06964v1 Announce Type: cross Abstract: Bridging the gap between human pilot intent and autonomous flight operation is critical for real-world electric vertical takeoff and landing (eVTOL) a
arXiv:2607.06796v1 Announce Type: cross Abstract: Deep learning has achieved remarkable success in various domains including time series analysis, computer vision and natural language processing. Howe
In this post, we walk through five capabilities now available in SageMaker HyperPod inference: multi-tier data capture for auditing and model improvement, direct deployment from Hugging Face Hub, loca
This post from Thariq on X likely promotes or announces additional content, updates, or expansions related to the Fable video game franchise. Without access to the specific tweet content, the post pro
arXiv:2607.06872v1 Announce Type: new Abstract: The increasing accessibility of artificial intelligence has led to a rapid rise in AI-generated videos, making it more difficult to distinguish between
arXiv:2607.06651v1 Announce Type: new Abstract: Federated learning (FL) over mobile and edge devices increasingly involves multimodal models in which clients differ in both sensing capability and comp
arXiv:2607.07178v1 Announce Type: cross Abstract: Recent breakthroughs of Reinforcement Learning (RL) have highlighted its potential for complex agentic Large Language Model (LLM) tasks. However, exis
Gené Teare / Crunchbase News: European startups raised 24B in Q2, up 66% YoY and the strongest quarter in four years; UK startups raised 10.4B, above Germany's 3.2B, and France's 2.4B — In Q2, Europe
arXiv:2607.07302v1 Announce Type: new Abstract: This paper reports an empirical study evaluating the relevance of several RAG metrics. The experiment is based on a question-answering dataset created b
arXiv:2607.06820v1 Announce Type: new Abstract: Recent advances in AI for Mathematics have focused largely on autoformalization and theorem proving, leaving the role of Computer Algebra Systems (CAS)
arXiv:2607.07251v1 Announce Type: new Abstract: One of the expected abilities of vision-language models (VLMs) is spatial reasoning ability based on a given text and image. To evaluate the spatial rea
Mark Zuckerberg promoted Meta's AI model on X (formerly Twitter), which Elon Musk highlighted as evidence that X has become the dominant platform for AI announcements and industry discourse. Musk's co
arXiv:2603.09385v2 Announce Type: replace Abstract: Event cameras offer superior sensitivity to high-speed motion and extreme lighting, making event-based monocular depth estimation a promising approa
arXiv:2607.06724v1 Announce Type: new Abstract: LLM-based robot planners are fluent but cannot guarantee that their plans are executable or safe. Classical PDDL planners can guarantee these properties
Enterprise artificial intelligence startup Corvic AI Inc. today released Corvic V5, a version of its platform built around reusing prompts, so when one gets the right answer, V5 can save it as a workf
arXiv:2508.17298v3 Announce Type: replace-cross Abstract: Compositional visual reasoning has emerged as a key research frontier in multimodal AI, aiming to endow machines with the human-like ability t
arXiv:2607.07545v1 Announce Type: new Abstract: Recent advances in generative Artificial Intelligence have made synthetic face images increasingly realistic, creating new challenges for multimedia for
arXiv:2607.06644v1 Announce Type: cross Abstract: Determinantal point processes have recently emerged as a kernel-based alternative to standard independent sampling for constructing efficient minibatc
arXiv:2607.07513v1 Announce Type: new Abstract: Self-supervised learning matches supervised accuracy from a fraction of the labels, but the labeled-sample efficiency behind this has lacked a theoretic
arXiv:2509.21160v2 Announce Type: replace-cross Abstract: With the growing use of large language models, concerns over content authenticity have spurred a variety of watermarking schemes. These scheme
arXiv:2508.12265v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable progress in reasoning across diverse domains. However, effective reasoning in real-world t
The race for fast token generation has moved from benchmark sheets into production data centers, and the hardware blueprint for winning it is no longer a GPU-only story. As agentic AI use cases multip
arXiv:2407.11217v4 Announce Type: replace-cross Abstract: Clustering problems such as k-means and k-median are staples of unsupervised learning, and many algorithmic techniques have been developed to
arXiv:2512.02076v2 Announce Type: replace-cross Abstract: We propose FDRMFL, a task-driven multimodal feature extraction framework for federated regression under non-IID data distributions. Extracting
arXiv:2607.07314v1 Announce Type: cross Abstract: Federated learning (FL) avoids explicit data exposure by keeping raw data on local clients, yet privacy risks remain in the training process and the l
Andrew Ackerman / Washington Post: Federal Reserve Chair Kevin Warsh names Marc Andreessen and Xbox CEO Asha Sharma to lead a task force on the economic impact of new technologies, including AI — The
arXiv:2606.17420v2 Announce Type: replace-cross Abstract: Tau positron emission tomography (PET) is widely used for the in vivo characterization of disease stage and progression in Alzheimer's disease
Wall Street Journal: Fidji Simo says she has decided to leave her full-time role at OpenAI and transition to being a part-time adviser after her medical condition worsened — The head of artificial gen
OpenAI's Fidji Simo is departing her full-time role as the company's AGI chief and is transitioning to being a 'part-time advisor,' she said on X. The news follows Simo's original announcement in Apri
arXiv:2607.06648v1 Announce Type: cross Abstract: Latent reasoning methods perform multi-step inference entirely in the model's continuous hidden states, promising more compact and efficient reasoning
arXiv:2607.06883v1 Announce Type: cross Abstract: We consider the problem of finding stationary points for stochastic convex optimization problems. Rather than surrogates to stationarity, such as a pr
arXiv:2607.06621v1 Announce Type: new Abstract: The pre-softmax score of an attention head is a bilinear form score(i,j) = x_i^T M x_j in a learned operator M = W_q^T W_k. Because M is generally non-s
arXiv:2501.10870v2 Announce Type: replace-cross Abstract: The principal objective of this work is twofold within nonparametric regression settings: (1) to establish the minimax optimal convergence rat
Last year, Image Line introduced Gopher for FL Studio, an AI chatbot that was basically a glorified instruction manual. You asked it how to do something, and it would serve up the relevant instruction
Recent research published in July 2026 suggests that Homo floresiensis scavenged the remains of Komodo dragon kills rather than hunting large prey as previously thought. This finding indicates a diffe
arXiv:2607.06957v1 Announce Type: cross Abstract: Realistic and diverse traffic simulation is essential to autonomous driving development. Yet prevailing benchmarks predominantly reward realism, and r
arXiv:2603.17390v2 Announce Type: replace Abstract: Material classification has emerged as a critical task in computer vision and graphics, supporting the assignment of accurate material properties to
arXiv:2607.07258v1 Announce Type: cross Abstract: In many realistic scenarios, large volumes of time series data are generated with limited or expensive annotations. This limitation makes supervised l
For coding agents, trustworthiness has to be tested in the harness where the model actually writes code. In one surveillance scenario, Kimi K2.7 complied with the request in 8/8 samples. SWE-1.7 refus
arXiv:2607.06615v1 Announce Type: cross Abstract: Image forgery detection is a critical task in digital forensics, yet many deep-learning localization approaches are typically GPU-accelerated and comp
I was really looking forward to July 4, and not just because I love a poolside barbecue. This year the American holiday also marked a big symbolic deadline for US nuclear power. Last year the Trump ad
arXiv:2607.07478v1 Announce Type: cross Abstract: FFT-based spectral preprocessing of learned query-key (Q/K) projections substantially improves transformer attention on character-level language model
arXiv:2506.04985v2 Announce Type: replace Abstract: Large language models (LLMs) require substantial compute, and thus energy, at inference time. While quantizing weights and activations is effective
arXiv:2607.07144v1 Announce Type: new Abstract: The key-value (KV) cache dominates the memory cost of long-context autoregressive inference, and a growing body of work compresses it through quantizati