Knowledge catalogue
arXiv:2602.06527v2 Announce Type: replace Abstract: Scaling test-time compute with multi-path chain-of-thought improves reasoning accuracy, but its effectiveness depends critically on the exploration-
arXiv:2605.09899v1 Announce Type: cross Abstract: Cross-modal knowledge distillation has emerged as an effective strategy for integrating point cloud and image features in 3D perception tasks. However
arXiv:2605.10628v1 Announce Type: new Abstract: Few-shot anomaly detection (FSAD) has made significant strides, yet existing methods still face critical challenges: (i) dependence on task- or dataset-
arXiv:2605.10164v1 Announce Type: new Abstract: Dense Associative Memory (DenseAM) is a promising family of AI architectures that is represented by a neural network performing temporal dynamics on an
arXiv:2605.10100v1 Announce Type: cross Abstract: We introduce HYPERPOSE, a novel 3D human pose estimation framework that performs spatio-temporal reasoning entirely within the Lorentz model of hyperb
arXiv:2604.15113v2 Announce Type: replace Abstract: Vector Symbolic Architectures (VSAs) provide a well-defined algebraic framework for compositional representations in hyperdimensional spaces. We int
arXiv:2601.22904v2 Announce Type: replace-cross Abstract: Recent studies have explored using pretrained Vision Foundation Models (VFMs) such as DINO for generative autoencoders, showing strong generat
arXiv:2605.08254v1 Announce Type: cross Abstract: As foundation models grow in capability, the ability to efficiently and reliably control their behavior becomes critical. Fine-tuning these models can
arXiv:2605.10224v1 Announce Type: new Abstract: Current AI-powered research systems adopt a direct search-then-summarize paradigm that treats hypotheses as end products of scientific discovery. We arg
arXiv:2605.10009v1 Announce Type: new Abstract: Query-based image retrieval (QBIR) requires retrieving relevant images given diverse and often stylistically heterogeneous queries, such as sketches, ar
I also agree with this comment that the current view of FDEs is likely too limited to actually catalyze organizational transformation. @emollick Are they doing org change, though? The army of forward
ForgePilot is a desktop workspace application designed for Ollama that combines local language model capabilities with development tools, including support for Model Context Protocol (MCP), web resear
A technique combining FLUX.1-dev and ControlNet to enhance image inpainting, where ControlNet guides FLUX.1-dev in generating accurate repairs while maintaining consistency with the original image sty
i like that there are models called bert and ernie, but in all seriousness, this update looks impressive ERNIE 5.1 is here 🚀 ERNIE 5.1 significantly reduces pretraining cost while compressing total pa
I love seeing a new eval with such low scores. When we announced GPT-5.5, almost every benchmark had a score above 50%. It's time to retire evals like GQPA and bring in a new set. The first ProgramBen
I needed to book flights for a bunch of upcoming travel. As always, I used Claude Cowork to do it. In the past, Cowork has been decent at booking flights, but with Opus 4.7, for the first time ever, i
I put my flight preferences in my Cowork instructions, then let Opus get to work. It opened my browser, navigated a bunch of websites, and booked everything for me. The result: Cowork booked 8 flights
I sat down with @JonHernandezIA in Madrid to discuss the growing risks and impacts of AI and the urgent need to improve our social, political, and technical safeguards. Thanks for an excellent convers
I need to check the actual content of this post to provide an accurate summary. A developer released a free, offline Stable Diffusion application for Android that enables local image generation withou
I think frontier model writing is good! It often has a sense of style & tone, variations in sentence structure & length, some great phrasing, etc But it also has some weak spots (fiction!) & clear tic
Before artificial intelligence can scale, governed enterprise AI has to prove it can be trusted. As companies move from pilots to production, the real test is whether platforms can bring automation, t
arXiv:2605.10560v1 Announce Type: new Abstract: This paper describes our system to SemEval-2026 Task 3 Track A Subtask 1 on Dimensional Aspect Sentiment Regression (DimASR). We propose a lightweight a
arXiv:2605.10407v1 Announce Type: new Abstract: Modern LLM APIs often reveal only top-K logit scores and censor the remaining vocabulary. We study the per-position distribution-recovery limits of this
arXiv:2403.18136v3 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) have gained popularity in numerous domains, yet they are vulnerable to backdoor attacks that can compromise their
arXiv:2602.22551v2 Announce Type: replace-cross Abstract: Cancer is often driven by specific combinations of an estimated two to nine gene mutations, known as multi-hit combinations. Identifying these
Palo Alto Networks Inc. today launched Idira, a new identity security platform designed to manage human, machine and artificial intelligence agent identities across the enterprise under a single privi
If you want to get a sense of the AI writing gap, just look at the horrible prompting jobs in the replies. “Write a hot take! In all lowercase! Add an analogy to randomly summarize the tweet - which n
This post likely discusses Tesla's autonomous driving capabilities, specifically how some users have become so reliant on autopilot or full self-driving features that they rarely manually control thei
arXiv:2605.08841v1 Announce Type: new Abstract: Vision-Language Models (VLMs) exhibit systematic bias toward visual illusions, recalling memorized facts rather than perceiving actual visual difference
arXiv:2605.09127v1 Announce Type: new Abstract: Contact-implicit trajectory optimization (CITO) has attracted growing attention as a unified framework for planning and control in contact-rich robotic
arXiv:2603.08558v2 Announce Type: replace Abstract: Learning compact state representations in Markov Decision Processes (MDPs) has proven crucial for addressing the curse of dimensionality in large-sc
arXiv:2601.20477v3 Announce Type: replace Abstract: We study the training dynamics of neural classifiers through the lens of binary hypothesis testing. We re-formalize classification as a collection o
arXiv:2512.02012v2 Announce Type: replace Abstract: MeanFlow (MF) has recently been established as a framework for one-step generative modeling. However, its ``fastforward'' nature introduces key chal
arXiv:2605.09256v1 Announce Type: cross Abstract: We introduce a use of the (M)-cover (or (M)-layer) transform for machine learning. The method replicates a model (M) times, but instead of coupling th
arXiv:2605.08577v1 Announce Type: new Abstract: In modern GANs, maintaining an Exponential Moving Average (EMA) of the generator's weights is a standard practice, as such an averaged model consistentl
arXiv:2605.10523v1 Announce Type: new Abstract: The field of image-to-video generation has made remarkable progress. However, challenges such as human limb twisting and facial distortion persist, espe
arXiv:2605.08950v1 Announce Type: cross Abstract: Lexical difficulty prediction is a fundamental problem in language learning and readability assessment, requiring models to estimate word difficulty a
arXiv:2605.10149v1 Announce Type: new Abstract: Temporal action segmentation (TAS) divides untrimmed videos into labeled action segments. While fully supervised methods have advanced the field, challe
arXiv:2603.00918v3 Announce Type: replace-cross Abstract: Text-to-image generation powers content creation across design, media, and data augmentation. Post-training of text-to-image generative models
arXiv:2605.08184v1 Announce Type: cross Abstract: This research addresses a validated TMS EEG cleaning pipeline and a corresponding benchmark dataset. It evaluates two widely used artifact removal pip
'In California, every professor has 10 different startups with their students. In some Canadian universities, it's one professor out of ten.' @jpineau1, Chief AI Officer at @Cohere at #WebSummitVancou
arXiv:2605.08295v1 Announce Type: cross Abstract: While random demonstration labels barely hurt in-context learning (Min et al., 2022), we show that homogeneous labels--even semantically valid ones--c
In KAME, a fast speech model starts replying instantly, while a backend LLM runs in parallel to inject deep knowledge on the fly. It’s a completely different way to approach conversational AI, making
arXiv:2512.21587v2 Announce Type: replace-cross Abstract: Spatial photonic Ising machines offer a novel optical platform for optimization and spin-model simulation, but existing diffraction-based sche
arXiv:2605.10269v1 Announce Type: new Abstract: Maritime object detection is critical for the safe navigation of unmanned surface vessels (USVs), requiring accurate recognition of obstacles from small
arXiv:2601.16097v2 Announce Type: replace Abstract: Large Language Models enable users to access database using natural language interfaces using tools like Text2SQL, Text2SPARQL, and Text2Cypher, whi
arXiv:2010.03496v4 Announce Type: replace-cross Abstract: Knowledge Graphs (KG) are of vital importance for multiple applications on the web, including information retrieval, recommender systems, and
arXiv:2605.10267v1 Announce Type: new Abstract: In industrial procurement, an LLM answer is useful only if it survives a standards check: recommended material must match operating condition, every par
arXiv:2605.09977v1 Announce Type: new Abstract: Spatio-temporal fetal brain atlases are important for characterizing normative neurodevelopment and identifying congenital anomalies. However, existing
arXiv:2605.10518v1 Announce Type: cross Abstract: Masked Diffusion Models (MDMs) have emerged as a promising alternative to autoregressive models in language modeling, offering the advantages of paral
arXiv:2605.08180v1 Announce Type: cross Abstract: Modern IoT and sensor networks generate vast amounts of data, posing significant challenges for storage, transmission, and real-time processing. Tradi
arXiv:2601.21926v4 Announce Type: replace Abstract: Diffusion-based visuomotor policies built on 3D visual representations have achieved strong performance in learning complex robotic skills. However,
arXiv:2602.05198v2 Announce Type: replace Abstract: Environmental monitoring robots often need to estimate data fields (e.g., salinity, temperature, bathymetry) under tight resource constraints. Class
arXiv:2605.10087v1 Announce Type: new Abstract: This paper describes an initiation of interaction(IoI) detection framework without keywords for human-robot interaction(HRI) based on audio and vision s
arXiv:2605.08832v1 Announce Type: new Abstract: Neural surrogate models for computational fluid dynamics (CFD) are typically trained as forward operators that map explicit problem specifications, such
arXiv:2605.08268v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in multi-agent systems where agents communicate in natural language to solve tasks jointly. A k
arXiv:2605.09803v1 Announce Type: cross Abstract: This research paper addresses the limitations of current mobile accessibility services like TalkBack, which provide manual gesture-based sequential fe
arXiv:2605.09273v1 Announce Type: new Abstract: We study online multicalibration beyond the worst-case. We give a single, efficient algorithm which dynamically interpolates between benign and worst-ca
arXiv:2605.10039v1 Announce Type: cross Abstract: Frontier coding agents read configuration files (CLAUDE.md, AGENTS.md, Cursor Rules) at session start and are expected to follow the conventions insid
arXiv:2602.03677v2 Announce Type: replace Abstract: Modality following is the ability to selectively leverage multimodal contexts based on user instructions. It is fundamental to the safety and reliab