Knowledge catalogue
arXiv:2606.31543v1 Announce Type: new Abstract: Large language models can produce fluent, internally coherent reasoning traces for abstract reasoning tasks while still being confidently wrong - making
Flat-rate AI plans are subsidizing agentic workloads. Learn why LLM inference costs are moving to metered pricing and how evals reveal cost per successful task. The post Model subsidies are ending. Wh
arXiv:2606.30695v1 Announce Type: cross Abstract: Single-cell drug perturbation models should predict not only transcriptional response magnitude, but also whether a treatment alters the proliferative
arXiv:2606.31644v1 Announce Type: new Abstract: As large language models take on morally consequential roles in healthcare, legal, and hiring contexts, we need to examine whether their ethical behavio
More and more developers turning to glm5.2 as a daily driver for coding Here’s how to use it with deepagents code You can start building with GLM 5.2 in minutes: 1️⃣ Download dcode 2️⃣ Select your mod
arXiv:2606.30940v1 Announce Type: cross Abstract: Deep learning methods have vastly expanded the capabilities of motion planning in robotics applications, as learning priors from large-scale data has
arXiv:2606.31383v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) typically employ resampling-based projectors to transform dense visual features into a compact token sequence f
arXiv:2606.31135v1 Announce Type: new Abstract: We present LINet (Linear Integration Network), a Multi-Stream Neural Network (MSNN) for RGB-D scene classification. Current multi-modal architectures tr
arXiv:2509.22476v2 Announce Type: replace Abstract: Robust medical image segmentation across modalities remains challenging due to severe domain shifts and the lack of target-domain labels. While diff
Multi-GPU kernels are the real test for coding models. Today at @aiDotEngineer, @simran_s_arora shared ParallelKernelBench, an open-source benchmark for evaluating whether LLMs can write fast CUDA ker
arXiv:2603.13748v3 Announce Type: replace Abstract: Real-world robots often operate in settings where objective priorities depend on the underlying context of operation. When the underlying context is
Multi-token Residual Prediction is a technique for improving language model inference efficiency by predicting multiple tokens simultaneously rather than one at a time, reducing latency and computatio
arXiv:2606.30857v1 Announce Type: new Abstract: This paper describes our submission to SemEval-2026 Task 9 on detecting multilingual, multicultural, and multievent online polarization. We address all
arXiv:2601.21173v2 Announce Type: replace-cross Abstract: With the rapid development of industrial intelligence and unmanned inspection, reliable perception and safety assessment for AI systems in com
arXiv:2312.00305v3 Announce Type: replace-cross Abstract: Many important tasks of large-scale recommender systems can be naturally cast as testing multiple linear forms for noisy matrix completion. Th
arXiv:2509.10406v4 Announce Type: replace Abstract: Pretraining transformers on long sequences (entire code repositories, collections of related documents) is bottlenecked by quadratic attention costs
arXiv:2606.30988v1 Announce Type: new Abstract: Robot manipulation often relies on sensory feedback beyond vision, particularly in contact-rich settings where force, tactile, or audio signals reveal i
arXiv:2606.30995v1 Announce Type: new Abstract: Recent work has shown that well-optimized individual decision trees can match complex black box models in some settings, primarily in noisy domains. For
arXiv:2606.31073v1 Announce Type: new Abstract: Large language models (LLMs) provide a promising interface for high-level robotic task planning, but their use in multi-UAV collaboration remains diffic
arXiv:2606.31811v1 Announce Type: new Abstract: Foundation models have transformed vision and language processing by providing rich, reusable representations that transfer across diverse tasks. Sheet
arXiv:2606.31533v1 Announce Type: new Abstract: Identifying and grounding precise geometric entities, such as edges, planar regions, and curved surfaces within 3D objects, is foundational to computer-
arXiv:2606.31919v1 Announce Type: cross Abstract: Zero-shot Object Goal Navigation (ZSON) with RGB-only perception poses a fundamental challenge for embodied agents, as the absence of explicit depth i
My prediction: the excitement for Fable 5 will wear off really fast. Reposting this to help those who will be extremely disappointed after they play with Fable 5 and run out of tokens or can't do much
Nano Banana 2 Lite is an image editing tool or model available through ComfyUI, a node-based interface for AI image generation and manipulation. This resource likely provides a lightweight version of
Nano Banana 2 Lite is now in Comfy. The fastest, cheapest model in the Nano Banana family. → 4-second image gen → $0.034 per 1K images If your pipeline runs on iteration volume, this changes the game.
Nano Banana 2 Lite is a text-to-image model optimized for efficiency and speed, likely designed for use within the ComfyUI node-based interface. This lightweight version of the model enables users to
NASA Administrator Jared Isaacman acknowledged the May 28, 2026 New Glenn rocket explosion at Cape Canaveral, noting that spaceflight development is extraordinarily difficult and pledging NASA's suppo
A NASA Office of Inspector General audit released June 30 found that Boeing's Starliner capsule will not achieve human-rating certification until 2027 at the earliest , representing a significant dela
arXiv:2602.18767v3 Announce Type: replace-cross Abstract: In Machine-Assisted Theorem Proving, a theorem proving agent searches for a sequence of expressions and tactics that can prove a statement in
Nemotron 3 Ultra is taking off on Together AI 🚀 In just days, it's climbed to 35B tokens/day on @OpenRouter. That's the community voting with their tokens for open models that are fast, efficient, and
arXiv:2606.30953v1 Announce Type: new Abstract: We introduce the Neuro-Bayesian-Symbolic Residual Attention Shallow Network (NBS-RASN), a hybrid neural architecture for explainable cybersecurity risk
Neurologyca, a company working on human-centric artificial intelligence, announced the launch of a research division on Tuesday dedicated to advancing AI models’ ability to understand and adapt to peo
Security leaders are now expected to protect business growth and clearly articulate security value to their board of directors, in addition to managing risk. While translating technical defense into m
NEW paper worth reading. (bookmark it) Autonomous research systems usually prove themselves on cherry-picked wins, human-framed topics, or a handful of preset tasks. FARS runs the full loop at scale i
arXiv:2606.30937v1 Announce Type: new Abstract: LiDAR semantic segmentation often degrades under real-world deployment due to evolving sensing conditions, while collecting new annotations for retraini
No country wins a race to superintelligence. An AI vastly smarter than us wouldn't be a weapon we control, we'd be handing control over to it. ControlAI's US Director Connor Leahy (@NPCollapse) on why
arXiv:2606.31933v1 Announce Type: new Abstract: We introduce VidPair-Halluc, a new benchmark for evaluating video hallucination in large video models (LVMs) under rigorous and controlled conditions. U
arXiv:2606.31427v1 Announce Type: new Abstract: Generative image steganography synthesizes stego images directly from secret information to achieve inherent security advantages. Latent Diffusion Model
arXiv:2606.31717v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) is commonly viewed as an update-space approximation to full fine-tuning, yet this view is incomplete for self-gated Transform
arXiv:2510.17917v2 Announce Type: replace-cross Abstract: Data unlearning aims to remove the influence of specific training samples from a trained model. In fine-tuning methods, data unlearning relies
Playground Fable 5 has completed development and is ready for building, prompting the reset of user rate limits to allow 5-hour and weekly usage quotas to refresh. This announcement indicates that the
Now The Fountainhead – arguably the better book: 1. There are two ways to exist: create from your own vision, or live by reflecting and pleasing others – Rand calls them the first-handers and the seco
arXiv:2606.31764v1 Announce Type: cross Abstract: Differentiable rendering of planar rational splines remains largely underexplored, despite their widespread use in vector graphics and design. Existin
NVIDIA and its partners are investing in American manufacturing, supply chains, energy grids and skilled workforces so the U.S. can produce the infrastructure needed for better healthcare, breakthroug
arXiv:2606.30807v1 Announce Type: cross Abstract: Generative models have recently seen rapid adoption in End-to-End (E2E) autonomous driving (AD), with diffusion-based denoising and vocabulary-based r
arXiv:2606.31025v1 Announce Type: new Abstract: Active flow control is a fundamental application in engineering. Recent advances in deep reinforcement learning have made progress in this field. Howeve
arXiv:2606.31600v1 Announce Type: cross Abstract: Conformal prediction and its variants, including the split conformal prediction, provide a distribution-free framework for uncertainty quantification
arXiv:2603.19127v2 Announce Type: replace Abstract: As Spoken Language Models (SLMs) integrate speech and text modalities, they inherit the safety vulnerabilities of their LLM backbone while introduci
arXiv:2606.31524v1 Announce Type: cross Abstract: The Self-Improving Alignment (SAIL) algorithm addresses distribution shift by reducing a bilevel formulation of the problem to an efficient, single-le
On the pod: 'Constrained Adaptive Rejection Sampling' with @ucsd_cse professor @lorisdanto. Hear how symbolic AI experts have navigated the LLM era and why the future of AI code generation depends on
arXiv:2601.13913v2 Announce Type: replace Abstract: Estimating 3D from 2D is one of the central tasks in computer vision. In this work, we consider the monocular setting, i.e. single-view input, for 3
One of the reasons we brought @xAIMemphis to Mississippi wasn’t just its record-breaking $20 billion investment. It was also because the company is a great corporate partner that’s committed to giving
arXiv:2606.31478v1 Announce Type: new Abstract: Autonomous research agents can now draft hypotheses, write code, run experiments, and produce papers, but they remain brittle when experiments fail. Und
arXiv:2606.31156v1 Announce Type: cross Abstract: RAG systems retrieve documents optimized for answering one query at a time. Yet enterprise users arrive with sessions, that is, coherent episodes of r
arXiv:2508.13836v2 Announce Type: replace-cross Abstract: Pruning is a core technique for compressing neural networks to improve computational efficiency. This process is typically approached in two w
arXiv:2606.31388v1 Announce Type: new Abstract: We introduce extbf{OVOW}, the first training-free system that reconstructs instance-level, simulation-ready 4D mesh scenes from a single monocular video
arXiv:2603.00759v2 Announce Type: replace Abstract: In this paper, we present an online method for converting an arbitrary geometric path, represented by a sequence of states, and generated by any pla
arXiv:2606.31061v1 Announce Type: cross Abstract: Tensor Train (TT) decomposition is a powerful technique for analyzing high-dimensional data. Existing algorithms for computing TT decompositions can b
Only supporting zero, one, or unlimited I think it was a @swyx tweet that put me onto it, but building in support for 2 of a thing inevitably leads to later needing 3 So the moment you need more than
arXiv:2606.31993v1 Announce Type: new Abstract: While robotic manipulation capabilities have advanced rapidly, physical safety remains a major barrier to deploying household robots: task success is in