Knowledge catalogue
arXiv:2604.15237v1 Announce Type: new Abstract: Reconstructing dense 3D geometry from continuous video streams requires stable inference under a constant memory budget. Existing O(1) frameworks primar
arXiv:2604.15285v1 Announce Type: cross Abstract: We study post-training interpretability for Support Vector Machines (SVMs) built from truncated orthogonal polynomial kernels. Since the associated re
arXiv:2604.15143v1 Announce Type: cross Abstract: This work simulates the developmental process of cortical neurogenesis, initiating from a single stem cell and governed by gene regulatory rules deriv
arXiv:2512.23578v3 Announce Type: replace Abstract: In this paper, we show that when spoken language models (SLMs) are instructed to speak in a specific speaking style at the beginning of a multi-turn
arXiv:2410.08329v3 Announce Type: replace Abstract: Computational wave imaging (CWI) extracts hidden structure and physical properties of a volume of material by analyzing wave signals that traverse t
arXiv:2604.14629v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have shown remarkable capabilities in joint vision-language understanding, but their large scale poses significant challen
arXiv:2604.14834v1 Announce Type: new Abstract: Recent advancements in whole-body control through deep reinforcement learning have enabled humanoid robots to achieve remarkable progress in real-world
Financial Times: SynMax: ~40% of US data centers due in 2026 are facing delays, with major sites for Microsoft, OpenAI, and others likely set back by more than three months — Delays to a swath of new
arXiv:2604.13041v1 Announce Type: cross Abstract: Table Structure Recognition (TSR) requires the logical reasoning ability of large language models (LLMs) to handle complex table layouts, but current
Real-time threat intelligence company Team Cymru Inc. today announced the launch of Total Insights Feed, a unified threat intelligence platform that is designed to replace legacy indicator list-based
arXiv:2509.15602v5 Announce Type: replace Abstract: Multimodal large language models (MLLMs) excel at general video understanding but struggle with fast, high-frequency sports like tennis, where rally
Tesla is officially launching in Estonia. The company is holding an opening event on April 24th at Ülemiste Center 'Bring your friends and family to see our models, take part in the day’s activities a
Tesla is suing the state of North Dakota because the state won't allow the company to open any showrooms/service centers and sell direct to consumers. North Dakota law prohibits vehicle manufacturers
arXiv:2604.14941v1 Announce Type: new Abstract: Communicating complex system designs or scientific processes through text alone is inefficient and prone to ambiguity. A system that automatically gener
arXiv:2604.14619v1 Announce Type: cross Abstract: In computational paralinguistics, detecting cognitive load and deception from speech signals is a heavily researched domain. Recent efforts have attem
In the latest sign of AI silly season, Allbirds, the shoe company, told the world it was now an AI company and briefly managed to septuple its stock price. The Newbird AI story is really just one of a
arXiv:2604.14414v1 Announce Type: new Abstract: Turn-level metrics are widely used to evaluate properties of multi-turn human-LLM conversations, from safety and sycophancy to dialogue quality. However
The handsome new book Maintenance: Of Everything, Part One, by the tech industry legend Stewart Brand, promises to be the first in a series offering “a comprehensive overview of the civilizational imp
The Claude Code hackathon is back for Opus 4.7. Join builders from around the world for a week with the Claude Code team in the room, with a prize pool of $100K in API credits. Apply by Sunday: https:
arXiv:2604.13114v1 Announce Type: cross Abstract: Code smells and software vulnerabilities both increase maintenance cost, yet they are often handled by separate tools that miss structural context and
The post praises a coding agent tracer/viewer tool available on Hugging Face, highlighting its quality and usefulness for developers working with agents. The tool appears to be part of the pi-mono dat
arXiv:2604.13417v1 Announce Type: cross Abstract: As Large Language Models (LLMs) are increasingly deployed in mission-critical software systems, detecting hallucinations and ``faked truthfulness'' ha
arXiv:2604.14363v1 Announce Type: new Abstract: Multimodal language models systematically underperform on visual perception tasks, yet the structure underlying this failure remains poorly understood.
arXiv:2604.14703v1 Announce Type: new Abstract: Although some existing image manipulation localization (IML) methods incorporate authenticity-related supervision, this information is typically utilize
arXiv:2604.14176v1 Announce Type: new Abstract: Generalized Category Discovery (GCD) leverages labeled data to categorize unlabeled samples from known or unknown classes. Most previous methods jointly
This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. The problem with thinking you’re part Neanderthal There’s a th
arXiv:2604.14558v1 Announce Type: new Abstract: This paper presents the NTIRE 2026 image super-resolution (imes4) challenge, one of the associated competitions of the NTIRE 2026 Workshop at CVPR 2026.
The Hermes Agent Creative Hackathon starts now 16 Days, $25k in Prizes Presented by @Kimi_Moonshot & @NousResearch For the tinkerers pushing Hermes Agent into creative domains: video, image, audio, 3D
DigitalOcean's Inference Cloud Memory Layer is a technical architecture component designed to optimize database performance by implementing an in-memory caching layer for faster data access and reduce
This post announces Ornstein3.6-35B-A3B-GGU, a fine-tuned variant of Qwen 3.6 35B model available on Hugging Face, with the author claiming it represents a high-quality optimization of the base model.
arXiv:2604.14807v1 Announce Type: cross Abstract: The rapid integration of large language models (LLMs) into everyday workflows has transformed how individuals perform cognitive tasks such as writing,
arXiv:2603.11875v2 Announce Type: replace-cross Abstract: Prompt injection defenses are often framed as semantic understanding problems and delegated to increasingly large neural detectors. For the fi
The one nag I have to add to the system prompt still: 'PLEASE remember and follow this CRITICAL guidance with great care: Do NOT end responses with follow-up offers like 'Want me to...', 'Let me know
arXiv:2604.14197v1 Announce Type: new Abstract: Large language model (LLM) performance depends heavily on prompt design, yet prompt construction is often described and applied inconsistently. Our purp
'The post all LLMs hate and want you to NOT SEE' ^^ Serious title, you can also discuss this with the LLM, it would be biased against it, as it's known at this point that memory is the true long term
“The sharpest drop came from people who used the model for direct answers, not from those who used it more like a hint system, which suggests the real issue is not AI exposure itself but replacing eff
arXiv:2512.03048v4 Announce Type: replace-cross Abstract: Static content-based AI value alignment is insufficient for robust alignment under capability scaling, distributional shift, and increasing au
arXiv:2507.02935v2 Announce Type: replace Abstract: Successful human-agent teaming relies on an agent being able to understand instructions given by a (human) principal. In many cases, an instruction
arXiv:2604.14332v1 Announce Type: new Abstract: Diffusion-model inference and overdamped Langevin dynamics are formally identical. A physical substrate that encodes the score function therefore equili
arXiv:2604.15301v1 Announce Type: new Abstract: Many SLT systems quietly assume that brief chunks of signing map directly to spoken-language words. That assumption breaks down because signers often cr
I've never been as charmed and frustrated by one gadget as I have with the Poetry Camera. It's a delightful object. White and cherry red with a color-matched woven strap, it looks playful and adorably
This feature is powered by Replit’s parallel agents, introduced in Agent 4. Replit can spin up separate copies of your project, work on them in parallel, and then combine the results at the end- handl
Thoth v3.15.0 is live. Talk to your AI from anywhere. It talks back from everywhere. 5 channels, full parity: WhatsApp, Discord, Slack, SMS, Telegram Streaming, reactions, media, slash commands New: X
arXiv:2604.14430v1 Announce Type: new Abstract: We present Three-Phase Transformer (3PT), a residual-stream structural prior for decoder-only Transformers on a standard SwiGLU + RMSNorm + RoPE + GQA b
arXiv:2601.12145v2 Announce Type: replace Abstract: Softmax attention struggles with long contexts due to structural limitations: the strict sum-to-one constraint forces attention sinks on irrelevant
Cursor is temporarily doubling the usage limits for Composer 2 through the end of the weekend, specifically within Cursor's new agents window feature. This promotion allows users to access increased c
arXiv:2604.14614v1 Announce Type: cross Abstract: We give an algorithm for PAC learning intersections of k halfspaces with a rho margin to within error arepsilon that runs in time extsf{poly}(k, areps
arXiv:2604.14345v1 Announce Type: new Abstract: As search depth increases in autonomous reasoning and embodied planning, the candidate action space expands exponentially, heavily taxing computational
arXiv:2507.15066v5 Announce Type: replace Abstract: Time series anomaly detection (TSAD) has traditionally focused on binary classification and often lacks the fine-grained categorization and explanat
arXiv:2604.14398v1 Announce Type: cross Abstract: Rotating detonation engines (RDEs) are a promising propulsion concept that may offer higher thermodynamic efficiency and specific impulse than convent
To go deeper on our new Life Sciences model series, research lead @joyjiao12 and product lead Yunyun Wang joined @AndrewMayne on the OpenAI Podcast to discuss how we’re building models for biology, dr
arXiv:2603.18373v2 Announce Type: replace Abstract: When VLMs answer correctly, do they genuinely rely on visual information or exploit language shortcuts? We introduce the Tri-Layer Diagnostic Framew
arXiv:2604.13737v1 Announce Type: cross Abstract: Recommender systems have historically developed along two largely independent paradigms: feature interaction models for modeling correlations among mu
arXiv:2604.15239v1 Announce Type: new Abstract: In this work, we revisit several key design choices of modern Transformer-based approaches for feed-forward 3D Gaussian Splatting (3DGS) prediction. We
arXiv:2604.15310v1 Announce Type: new Abstract: This paper presents a method for image relighting that enables precise and continuous control over multiple illumination attributes in a photograph. We
arXiv:2604.14237v1 Announce Type: new Abstract: Transistor topology optimization is a critical step in standard cell design, directly dictating diffusion sharing efficiency and downstream routability.
arXiv:2601.10120v2 Announce Type: replace-cross Abstract: Optimizing communication topology in LLM-based multi-agent system is critical for enabling collective intelligence. Existing methods mainly re
arXiv:2510.25892v2 Announce Type: replace Abstract: We propose a graph-topological approach to active learning that directly targets the core challenge of exploration versus exploitation under scarce
arXiv:2510.27420v3 Announce Type: replace Abstract: Multi-embodiment grasping focuses on developing approaches that exhibit generalist behavior across diverse gripper designs. Existing methods often l
arXiv:2506.08080v2 Announce Type: replace-cross Abstract: Particle physics theories, such as those which explain neutrino flavor mixing, arise from a vast landscape of model-building possibilities. A