Knowledge catalogue
arXiv:2605.21724v1 Announce Type: new Abstract: Hyper-Connections (HC) improve residual networks by introducing learnable mixing across multiple residual streams, but unconstrained mixing leads to tra
arXiv:2605.22740v1 Announce Type: new Abstract: Decision trees partition the feature space using hard binary thresholds, assigning identical confidence to instances far from a decision boundary and to
arXiv:2605.22737v1 Announce Type: new Abstract: Distillation attacks create a deployment trade-off for model providers: the same outputs that make a model more useful can also make it easier to imitat
The Journal of the @americanacad just published a new issue of Daedalus on AI and Science, edited by James Manyika. It has terrific line-up of contributors, including @demishassabis, @ylecun, Josh Ten
arXiv:2605.22498v1 Announce Type: new Abstract: Scientific machine learning often requires combining known physics with unknown parameters or correction terms learned from data. Existing approaches ei
arXiv:2605.22723v1 Announce Type: new Abstract: A central error measure in Gaussian DDPMs is the path-space KL divergence between the exact reverse chain and the learned Gaussian reverse process. This
arXiv:2605.21798v1 Announce Type: new Abstract: Neural processes amortize Gaussian process inference, replacing the exact O(n^3) posterior with a learned O(n) map from context sets to predictive distr
arXiv:2605.22365v1 Announce Type: cross Abstract: Time Series Forecasting (TSF) plays a critical role across many domains, yet it is vulnerable to backdoor attacks. However, backdoor defenses tailored
arXiv:2605.21553v1 Announce Type: new Abstract: Tokens are becoming the basic units through which foundation models represent and process information for understanding and inference. However, traditio
arXiv:2605.21999v1 Announce Type: new Abstract: Adversarial Distillation aims to enhance student robustness by guiding the student with a robust teacher's soft labels within the min-max adversarial tr
arXiv:2605.22377v1 Announce Type: new Abstract: Transformer-based language models such as BERT having 110M+ parameters have revolutionized natural language understanding, yet their internal mechanisms
arXiv:2601.22365v2 Announce Type: replace-cross Abstract: The Gilbert-Pollak Conjecture itep{gilbert1968steiner}, also known as the Steiner Ratio Conjecture, states that for any finite point set in th
arXiv:2603.04383v2 Announce Type: replace-cross Abstract: YouTube has evolved into a powerful platform where creators monetize their influence through affiliate marketing, raising concerns about trans
arXiv:2603.21717v4 Announce Type: replace Abstract: Distribution-to-distribution generative models support scientific imaging tasks ranging from modeling cellular perturbation responses to translating
arXiv:2605.22765v1 Announce Type: new Abstract: Discrete diffusion models are often trained through clean-data prediction, but the prediction can be used in different ways to define the reverse dynami
arXiv:2605.22010v1 Announce Type: cross Abstract: We consider one-hidden layer neural networks trained in the feature-learning regime using gradient descent, and relate the output of the finite-width
arXiv:2508.03556v3 Announce Type: replace Abstract: Process Reward Model (PRM) is widely used in the post-training of Large Language Model (LLM) because it can perform fine-grained evaluation of the r
arXiv:2605.22481v1 Announce Type: new Abstract: Backdoor poisoning attacks behave counter-intuitively in high dimensions: stronger training triggers can help the defender. We study regularised general
Why? Most green-card applicants will need to go abroad to apply for permanent residency at an American consulate, rather than filing from within the U.S. as they do now, the Trump administration annou
arXiv:2605.22472v1 Announce Type: new Abstract: Winner-take-all (WTA) networks constitute a central circuit motif in cortical networks of the brain. In addition, WTA-like activations are abundant in m
arXiv:2605.21707v1 Announce Type: cross Abstract: We describe an adaptive market-making architecture that preserves the analytical structure of the Avellaneda--Stoikov framework while introducing a su
arXiv:2605.22342v1 Announce Type: new Abstract: While 4D Gaussian Splatting (4DGS) has revolutionized high-fidelity dynamic reconstruction, safeguarding the intellectual property of these assets remai
arXiv:2605.22216v1 Announce Type: new Abstract: This report presents our solution for the WeatherProof Dataset Challenge, namely CVPR 2026 8th UG2+ Challenge Track 2: Semantic Segmentation in Adverse
arXiv:2605.21642v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly augmented with continuous or latent non-textual tokens intended to support 'visual thinking.' Despite imp
arXiv:2506.04708v3 Announce Type: replace Abstract: Language models have demonstrated remarkable capabilities in reasoning tasks through test-time scaling techniques like best-of-N sampling and tree s
arXiv:2605.22132v1 Announce Type: new Abstract: Pretrained vision foundation models deliver strong performance across tasks with limited fine-tuning. However, their Vision Transformer (ViT) backbones
arXiv:2509.00303v3 Announce Type: replace-cross Abstract: In this work, we present the exttt{LLM ORDER BY} semantic operator as a logical abstraction and conduct a systematic study of its physical imp
arXiv:2605.22183v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for generalist robotic manipulation. A common design in current architectures m
arXiv:2605.22259v1 Announce Type: cross Abstract: Heterogeneous sensor fusion is vital for detecting, localizing, and classifying CBRNE threats. However, individual sensors are often only capable of d
arXiv:2605.21835v1 Announce Type: cross Abstract: The synergistic interpretation of anatomical information from computed tomography (CT) and metabolic information from positron emission tomography (PE
arXiv:2605.21836v1 Announce Type: new Abstract: Soft sleeve actuators (SSAs) have recently been developed as a pneumatic actuation approach for wearable and assistive robotic systems. By integrating t
arXiv:2605.22435v1 Announce Type: new Abstract: Hate speech and misinformation frequently co-occur online, amplifying prejudice and polarization. Given their scale, using Large Language Models (LLMs)
arXiv:2209.03358v5 Announce Type: replace-cross Abstract: Spiking neural networks (SNNs) have attracted much attention for their high energy efficiency and recent advances in classification performanc
arXiv:2605.22344v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) and diffusion models have each reached remarkable maturity: MLLMs excel at reasoning over heterogeneous multimo
arXiv:2605.22050v1 Announce Type: new Abstract: While diffusion models excel at generating high-quality images, their tendency to memorize training data poses significant privacy and copyright risks.
arXiv:2605.22819v1 Announce Type: new Abstract: Camera pose matters. The position and orientation of each viewpoint define a shared spatial coordinate frame that relates observations across video fram
arXiv:2602.02214v3 Announce Type: replace Abstract: To achieve real-time interactive video generation, current methods distill pretrained bidirectional video diffusion models into few-step autoregress
arXiv:2605.22563v1 Announce Type: new Abstract: Training Deep Neural Networks for tracking individual cells in biomedical videos requires a large amount of annotated data. The annotation of videos for
arXiv:2605.22616v1 Announce Type: new Abstract: Understanding how conceptual knowledge is grounded in bodily experience, and to what extent machine systems can acquire such knowledge without direct se
arXiv:2605.21949v1 Announce Type: new Abstract: Medical RAG systems in high-risk QA settings are often evaluated through a single answer-or-abstain decision, but mixed evidence may support one claim,
arXiv:2605.22002v1 Announce Type: new Abstract: Biomedical image segmentation is a critical task in medical diagnosis and treatment planning, enabling precise delineation of anatomical structures and
arXiv:2603.16672v2 Announce Type: replace-cross Abstract: Misinformation on social media undermines informed decision-making and public trust. Prebunking offers a proactive complement by helping users
arXiv:2605.22249v1 Announce Type: new Abstract: Accurate brain tumor segmentation using multiparametric MRI is critical for effective treatment planning. However, in clinical settings, complete acquis
arXiv:2605.22605v1 Announce Type: cross Abstract: Object detection from Unmanned Aerial Vehicles (UAVs) is challenged by severe ego-motion, camera jitter, and large scale variations. While modern dete
arXiv:2605.22777v1 Announce Type: new Abstract: Representation Autoencoders (RAEs) leverage frozen vision foundation models (VFMs) as tokenizer encoders, providing robust high-level representations th
arXiv:2605.22411v1 Announce Type: new Abstract: Large language model (LLM) agents still struggle with long-term memory question answering, where answer-supporting evidence is often scattered across lo
arXiv:2605.21390v1 Announce Type: cross Abstract: We examine how people experience two choices in the design of generative ghosts, AI systems that are trained on data of the dead: representation, wher
arXiv:2605.21540v1 Announce Type: cross Abstract: The proliferation of large language models has introduced a new paradigm of synthetic political communication in which narratives may be generated, se
arXiv:2605.21146v1 Announce Type: cross Abstract: Modern DNNs are repeatedly fine-tuned to incorporate new data and functionality. This evolutionary workflow introduces a security risk when updated da
arXiv:2605.22290v1 Announce Type: new Abstract: Accurate detection and counting of virus patches in focus-forming unit (FFU) images, also known as foci images, are important for quantifying viral infe
arXiv:2605.22255v1 Announce Type: new Abstract: The digitization of musical scores plays a crucial role in their preservation and accessibility, yet information retrieval still depends mainly on metad
arXiv:2605.22170v1 Announce Type: new Abstract: In recent years, several Speech Language Models (SLMs) that represent speech and written text jointly have been presented. The question then emerges abo
arXiv:2401.00139v3 Announce Type: replace-cross Abstract: This paper introduces a causal attribution model to enhance the interpretability of large language models (LLMs) and improve their causal reas
arXiv:2605.22607v1 Announce Type: new Abstract: Gaze following requires both scene understanding and gaze reasoning to localize the gaze target of an in-scene person. Recently, vision foundation model
arXiv:2605.22078v1 Announce Type: cross Abstract: Recent advances in Multimodal Large Language Models (MLLMs) have significantly advanced video understanding tasks, yet challenges remain in efficientl
arXiv:2605.21649v1 Announce Type: cross Abstract: Long-context decoding is increasingly limited by KV-cache memory traffic since each generated token attends over a cache whose size grows linearly wit
arXiv:2605.21970v1 Announce Type: cross Abstract: Accurate and robust medical image classification is paramount for early disease diagnosis and treatment planning. However, challenges such as limited
arXiv:2605.22391v1 Announce Type: cross Abstract: We present Epicure, a family of three sibling skip-gram ingredient embeddings retrained from scratch on a multilingual recipe corpus. We aggregate 4.1
arXiv:2605.22203v1 Announce Type: new Abstract: In this study, we compare the performance of four text chunking approaches: Recursive, Khmer-Aware, Sentence-Based, and LLM-Based within a Retrieval-Aug
arXiv:2605.21862v1 Announce Type: new Abstract: Chunked vision-language-action (VLA) policies predict multi-step robot controls, conditioning each update on the current visual observation alone. Yet r