Knowledge catalogue
arXiv:2602.09611v2 Announce Type: replace-cross Abstract: Watermarking has emerged as a pivotal solution for content traceability and intellectual property protection in large vision language models (
arXiv:2607.24814v1 Announce Type: new Abstract: Access to specialist clinical expertise remains severely limited across sub-Saharan Africa, where physician-to-patient ratios can fall below 1:25,000 in
arXiv:2503.07303v3 Announce Type: replace Abstract: Texts, whether literary or historical, exhibit structural and stylistic patterns shaped by their purpose, authorship, and cultural context. Formulai
arXiv:2607.24774v1 Announce Type: new Abstract: Nuclear radiation, the energy released during atomic decay, poses persistent risks to public health and the environment, and concerns have only grown si
arXiv:2607.25327v1 Announce Type: new Abstract: Repeated human-robot interaction (HRI) requires proactively accounting for humans who continually adapt to evolving beliefs about the robot. Prior frame
Hey everyone, I recently finished pre-training BetterGPT-150M, a small, lightweight causal language model with ~152 million parameters.Trained on 15B tokens. Dataset & Training: Trained across stable
arXiv:2607.25045v1 Announce Type: new Abstract: Electroencephalography (EEG) analysis in cognitive studies requires specialized expertise and involves many defensible choices over contrasts, channels,
arXiv:2607.25487v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models translate natural-language commands into robot action sequences, but leading systems on the LIBERO-Plus robustness b
arXiv:2607.25750v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) fine-tuning has made it cheap and easy to customize open-weight image generation models for specific tasks, including the pro
arXiv:2507.00411v2 Announce Type: replace Abstract: Learning from ambiguous labels is a long-standing problem in practical machine learning applications. The purpose of partial label learning (PLL) is
arXiv:2408.03291v4 Announce Type: replace Abstract: Vision Transformers (ViTs) have gained significant attention, but their high computing cost limits the practical applications. While post-training q
arXiv:2607.25791v1 Announce Type: new Abstract: Falls represent a critical public health challenge, and accurate detection of the impact moment when an individual hits the ground is crucial for timely
arXiv:2603.02565v2 Announce Type: replace-cross Abstract: The Generator-Evaluator (G-E) framework generates K candidate sequences and uses an evaluator to select the highest-scoring one, which is wide
arXiv:2607.25820v1 Announce Type: new Abstract: Food image segmentation plays a vital role in health-related applications such as nutrition tracking and personalized health monitoring. However, existi
Figure 1: CUDA-to-MLX optimization translation map. CUDA optimization knowledge can be translated into architecture-native MLX strategies rather than copied instruction-for-instruction. We face a new
arXiv:2607.24764v1 Announce Type: new Abstract: The rapid growth of online grocery shopping requires recommendation systems that capture cyclical purchasing behavior and diverse user intents. Traditio
arXiv:2607.25503v1 Announce Type: new Abstract: Computational cytology on whole-slide images is challenging because malignant cells are rare, heterogeneous, and annotated slides are scarce. Anomaly de
arXiv:2607.24779v1 Announce Type: new Abstract: Online advertising bidding systems typically deploy multiple offline-trained expert models (e.g., PID controllers, model predictive control, offline RL
arXiv:2607.25583v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) and low-bit quantization are now standard tools for adapting language models under tight compute budgets, yet the
i'll say it plainly, hermes agent desktop is the best agentic app i've used, and i'm a little mad i didn't find it sooner. it auto see the models i'm serving, laguna s 2.1 sitting on my dgx spark and
arXiv:2607.26056v1 Announce Type: new Abstract: Forward latent world models predict how actions change a scene, but recover actions for a desired change only through expensive test-time search. We int
arXiv:2607.25132v1 Announce Type: new Abstract: A central challenge in interpreting learned decision-making systems is to determine whether their internal representations contain concepts that help ex
arXiv:2607.24900v1 Announce Type: new Abstract: Language model alignment aims to make model behavior reliably reflect desirable properties such as helpfulness, safety, and instruction following. Curre
arXiv:2607.25579v1 Announce Type: cross Abstract: Entity alignment (EA) identifies entities across knowledge graphs (KGs) that refer to the same real-world object. Conventional EA methods mainly explo
arXiv:2607.25241v1 Announce Type: cross Abstract: Standard offline reinforcement learning (RL) algorithms typically assume that the actions in the dataset are observed without error. However, in many
arXiv:2508.14003v4 Announce Type: replace-cross Abstract: The H-theorem provides a microscopic foundation for the Second Law of Thermodynamics and therefore occupies a central place in statistical phy
arXiv:2607.24904v1 Announce Type: cross Abstract: Standard vision-language models (VLMs) suffer from Moravec's paradox: they excel at complex offline visual reasoning but struggle with simple streamin
arXiv:2607.26016v1 Announce Type: cross Abstract: Recently, photonic transformer accelerators (PTAs) have successfully achieved significant speedup and energy efficiency improvements over electronic a
arXiv:2607.24765v1 Announce Type: cross Abstract: Large language models (LLMs) can give different answers to the same decision problem across runs, and reverse a decision when their own prior answer r
arXiv:2607.24838v1 Announce Type: cross Abstract: In medical multiple-choice question answering (MCQA), Retrieval-Augmented Generation (RAG) can supplement the domain knowledge of language models (LMs
arXiv:2607.24789v1 Announce Type: cross Abstract: We present NEXT (Next-interest EXploration Transformer), a reasoning-driven video recommendation framework that reasons over the video a user has just
arXiv:2607.25210v1 Announce Type: new Abstract: Oblique-view urban remote sensing imagery inevitably exhibits geometric projection displacements between building roofs and footprints, leading to signi
arXiv:2607.25164v1 Announce Type: cross Abstract: A CT examination captures multiple organs, but many biomedical questions concern abnormalities, prognosis, or longitudinal change in a specific organ.
arXiv:2607.26004v1 Announce Type: new Abstract: Generation in video diffusion or flow models is computationally expensive due to the slow and iterative sampling process. Current state-of-the-art (SOTA
arXiv:2603.26136v3 Announce Type: replace Abstract: Message Passing Neural Networks (MPNNs) have achieved strong performance on tasks involving relational data. However, small perturbations to graph s
arXiv:2607.25915v1 Announce Type: new Abstract: Complex structured reasoning tasks often require additional computation, yet current language models obtain it mainly by increasing parameter scale or b
arXiv:2512.17351v2 Announce Type: replace Abstract: Understanding architectural differences in language models is challenging, especially at academic-scale pretraining (e.g., 1.3B parameters, 100B tok
arXiv:2607.25157v1 Announce Type: new Abstract: Discrete masked diffusion language models support bidirectional generation and infilling, but adapting pretrained autoregressive (AR) transformers requi
arXiv:2607.24770v1 Announce Type: new Abstract: Procedural tasks such as furniture assembly and home repair impose substantial cognitive demands because users must interpret instructions, track task p
arXiv:2607.25826v1 Announce Type: new Abstract: Surface electromyography (sEMG) enables the control of prostheses, allowing upper-limb amputees to re-gain some hand function. Most current research foc
we're experimenting with our own dynamic GGUF quants of kimi k3, made from the original weights with our llama.cpp fork. Q3_K_S is done and works 1114.76 GiB on disk. Q1 and Q2 are in progress, result
arXiv:2601.20043v2 Announce Type: replace Abstract: Standard Bayesian Optimization (BO) assumes uniform smoothness across the search space an assumption violated in multi-regime problems such as molec
arXiv:2607.25422v1 Announce Type: new Abstract: Knowledge-intensive multimodal question answering (KI-MMQA) sits at the intersection of three expensive primitives: long visual token sequences, dense r
arXiv:2607.25912v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have shown strong potential for general robot manipulation, but most existing models rely on 2D visual-language ba
arXiv:2607.25041v1 Announce Type: cross Abstract: A growing number of applications, such as biometrics and retrieval-augmented generation (RAG), rely on cosine similarity scores computed between vecto
arXiv:2511.16618v2 Announce Type: replace Abstract: Surgical scene understanding demands temporally consistent tracking of instruments and tissues. For clinical use, such tracking should generalize to
arXiv:2607.24781v1 Announce Type: cross Abstract: RAG systems rely on chunking, which destroys structural information in documents. Existing heading-based retrieval (Jeong et al., 2025) requires multi
Thrilled to have @gabepereyra speak at our @sequoia event tmrw on OWN YOUR AI: how to build your own Lab as an application company. Also featuring @FireworksAI_HQ @mercor_ai @LangChain @trajectorylabs
arXiv:2607.25216v1 Announce Type: cross Abstract: Semantic ID-based generative recommendation tokenizes each item into a sequence of discrete semantic IDs and predicts the next item by generating sema
arXiv:2505.14366v2 Announce Type: replace Abstract: We present a conceptual framework for training Vision-Language Models (VLMs) to perform Visual Perspective Taking (VPT), a core capability for embod
arXiv:2607.24995v1 Announce Type: new Abstract: Semantic IDs (SIDs) are now a central component of generative recommendation. Current SID-based systems assign three roles to the same token sequence. S
arXiv:2607.26017v1 Announce Type: new Abstract: Memory is essential for LLM agents to accumulate task experience and reuse task-specific execution strategies. However, real-world deployment over bound
arXiv:2607.25870v1 Announce Type: cross Abstract: Voice activity detection (VAD) triggers downstream speech processing in always-on systems under strict memory, latency, and compute constraints. Recen
arXiv:2607.25209v1 Announce Type: cross Abstract: Generative recommendation commonly represents items using fixed-length semantic identifiers (SIDs) constructed through clustering and quantization. Ho
arXiv:2607.25234v1 Announce Type: new Abstract: Stereo depth estimation for driving, robotics and augmented reality must run at high resolution under tight latency budgets, yet in transformer-based ma
arXiv:2607.26037v1 Announce Type: new Abstract: We present Wonder, a general-purpose video world model for real-time, camera-controllable world exploration. Given an image or a conditional video, Wond
arXiv:2607.23869v1 Announce Type: cross Abstract: Randomized features provide a scalable approximation to kernel machines, but their performance depends strongly on the choice of feature distribution.
arXiv:2607.23882v1 Announce Type: new Abstract: Modern System-on-Chip (SoCs) often contain hundreds of millions to tens of billions of gates, making existing Hardware Trojan (HT) detection methods imp
At AMD’s Advancing AI event, Lisa Su called her shot – just like Babe Ruth. The question now is whether AMD has built the engineering machine to hit it. Last week, we argued that AMD’s next reinventio
arXiv:2607.22934v1 Announce Type: cross Abstract: Learning causal graphs from interventional data is a challenging problem with broad applications. In molecular biology, for example, a central goal is