Knowledge catalogue
arXiv:2601.03570v2 Announce Type: replace Abstract: Human beings primarily understand the world through concepts (e.g., dog), abstract mental representations that structure perception, reasoning, and
arXiv:2608.17151v1 Announce Type: new Abstract: Cell mimicry arises when different cell types appear morphologically similar. Human pathologists resolve this ambiguity using surrounding tissue context
arXiv:2608.18062v1 Announce Type: new Abstract: Language model tokenizers are typically selected with minimal evaluation, despite the fact that their design choices directly impact model capabilities.
arXiv:2608.17530v1 Announce Type: new Abstract: Continual pre-training of large language models must acquire new information without erasing old knowledge. Existing replay methods often choose a globa
arXiv:2608.16873v1 Announce Type: new Abstract: High-fidelity finite-element simulations can provide accurate numerical predictions for side-branch resonators, but large simulation datasets are expens
arXiv:2608.16190v1 Announce Type: cross Abstract: Trusted monitoring has a cheap, trusted model score a stronger untrusted model's actions, and a diverse ensemble of them beats a single stronger monit
arXiv:2608.16612v1 Announce Type: cross Abstract: An accurate estimation of the state of health (SOH) underpins a safe and optimized use of the battery system. Although compelling, data-driven SOH est
arXiv:2608.14662v1 Announce Type: cross Abstract: Accurate recognition of pain using physiological signals remains a challenging problem due to pain's subjective nature and high inter-individual varia
arXiv:2603.18739v4 Announce Type: replace Abstract: Deploying high-performance dense prediction models on resource-constrained edge devices remains challenging due to strict computation and memory bud
arXiv:2608.15580v1 Announce Type: new Abstract: Reliable endoscopic polyp reporting requires integrating quantitative lesion sizing, standardized Paris classification, and clinically meaningful morpho
arXiv:2608.15875v1 Announce Type: new Abstract: Vision-language-action (VLA) models have become a dominant paradigm for generalist embodied agents, demonstrating strong complex and long-horizon task c
arXiv:2608.15770v1 Announce Type: new Abstract: Designing effective trading strategies using reinforcement learning remains challenging due to delayed and noisy rewards, poor exploration, and the diff
arXiv:2608.14658v1 Announce Type: cross Abstract: We introduce pico-type, a byte-level multi-head content classifier with approximately 1.5 million parameters that simultaneously predicts seven conten
arXiv:2608.16793v1 Announce Type: new Abstract: Unified image restoration (UIR) aims to recover high-quality (HQ) content from low-quality (LQ) images with different degradations using a single model.
arXiv:2602.20839v3 Announce Type: replace Abstract: Training-free image editing with diffusion models is highly desirable yet is complex and remains a significant challenge. While recent optimisation-
arXiv:2608.16661v1 Announce Type: new Abstract: Hyperspectral reflectance spectroscopy enables non-destructive estimation of plant functional traits, yet current deep learning approaches process spect
arXiv:2608.13760v1 Announce Type: cross Abstract: Which reasoning behaviors are associated with correct answers in reasoning models, and does reasoning-oriented training amplify those behaviors? This
arXiv:2608.14227v1 Announce Type: new Abstract: Preprocessing invariance is an appealing goal for spectral foundation models: a frozen model should remain useful when laboratories preprocess spectra d
arXiv:2607.14975v2 Announce Type: replace Abstract: Channel foundation models (CFMs) are commonly evaluated in model-specific pipelines that differ in data, radio configurations, partitions, adaptatio
arXiv:2608.13866v1 Announce Type: cross Abstract: Large language models (LLMs) can generate synthetic training data for text classification, but the quality of generated samples is heterogeneous: some
arXiv:2608.13947v1 Announce Type: new Abstract: High-quality creative writing data for large language models (LLMs) remains dominated by story-centric data, limiting models' ability to follow the stru
arXiv:2608.13597v1 Announce Type: cross Abstract: Coverless image steganography (CIS) synthesizes a stego image rather than modifying an existing cover image, enabling authorized recipients to reconst
arXiv:2608.14046v1 Announce Type: new Abstract: In this work, we propose a source-agnostic framework that dynamically refines a binary mask throughout the reverse diffusion process by computing the di
arXiv:2608.12971v1 Announce Type: new Abstract: Face recognition systems have been shown to be biased toward certain demographic groups by exhibiting different error rates across gender, age, or ethni
arXiv:2608.13072v1 Announce Type: new Abstract: Electroencephalography (EEG) decoding models often generalize poorly across datasets and subjects due to domain shifts in acquisition protocols and indi
arXiv:2608.13463v1 Announce Type: cross Abstract: Modern image classification models excel when trained on single task-specific datasets but often struggle to generalize across domains and difficulty
arXiv:2608.13129v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong results on mathematical reasoning benchmarks yet remain unreliable on elementary numerical tasks, including
arXiv:2608.13283v1 Announce Type: new Abstract: Understanding motion in daily living requires context beyond kinematics, because similar inertial patterns during activities of daily living (ADLs) can
arXiv:2608.12078v1 Announce Type: cross Abstract: Learning world models from offline trajectories enables agents to accomplish different tasks through planning. Object-centric (OC) representations, wh
arXiv:2608.10296v1 Announce Type: new Abstract: One might imagine that architectural variations within the dense transformer paradigm have a limited effect on accuracy. However, we demonstrate that th
arXiv:2608.10525v1 Announce Type: cross Abstract: Historical context integration presents a fundamental challenge for Vision-Language Models (VLMs) in sequential decision-making tasks. Current VLMs pr
Four small architecture decisions can cost up to 47% of a model's long-context performance. New research from Ai2, Carnegie Mellon, and the University of Washington isolates them. Normalization, GQA,
arXiv:2608.10864v1 Announce Type: new Abstract: Vision-language models (VLMs) have achieved strong image and video understanding, yet their visual-spatial representations remain geometrically fragile,
arXiv:2604.07095v2 Announce Type: replace Abstract: Do multilingual embedding models encode a language-general representation of proficiency? We investigate this by training linear and non-linear prob
arXiv:2608.11142v1 Announce Type: new Abstract: Agricultural monitoring faces unique challenges, arising from the landscape's complex temporal, phenological, and climate dynamics, yet monitoring them
arXiv:2608.10708v1 Announce Type: new Abstract: Recent Vision Foundation Models (VFMs) predict depth, camera pose, and pointmap in a single forward pass without per-scene optimization, achieving stron
arXiv:2608.09995v1 Announce Type: cross Abstract: Joint demosaicing and denoising is a fundamental step in camera image signal processing, yet remains challenging because different Bayer-like color fi
arXiv:2608.11013v1 Announce Type: new Abstract: Text-only training is a popular paradigm in zero-shot video captioning, where the video distribution is not available to the model during training, lead
arXiv:2608.10836v1 Announce Type: cross Abstract: The signal ambiguity of whispered speech drives ASR systems toward two opposing failure modes: failing to capture whispered speech or hallucinatory tr
arXiv:2608.08319v1 Announce Type: new Abstract: Brain magnetic resonance imaging (MRI) is central to neuroscience and clinical assessment, but models are commonly developed for individual diseases, po
arXiv:2608.07822v1 Announce Type: cross Abstract: Quaternion-valued neural networks and variational quantum circuits (VQCs) both derive local transformations from SU(2) geometry, yet their performance
arXiv:2608.07693v1 Announce Type: cross Abstract: Generative traffic video forecasting aims to synthesize long-horizon, temporally coherent future videos of traffic scenes from a short observation his
arXiv:2608.07981v1 Announce Type: new Abstract: Streaming world models predict future visual states online while maintaining physically coherent dynamics over long horizons. However, their rollouts of
arXiv:2608.08148v1 Announce Type: cross Abstract: Attention mechanisms have been widely utilized in modern deep learning, and many existing multi-omics models inherit their conventional use to allow u
arXiv:2608.09493v1 Announce Type: new Abstract: Long-horizon future-frame prediction is important for autonomous driving, traffic surveillance, and intelligent transportation systems, yet remains chal
arXiv:2608.07894v1 Announce Type: new Abstract: Recent advances have highlighted the potential of machine learning, particularly Large Language Models (LLMs), for analyzing and optimizing programs. We
arXiv:2608.09633v1 Announce Type: new Abstract: Face presentation attack detection (PAD) aims to reliably detect a wide range of presentation attacks. While PAD methods achieve strong performance with
arXiv:2608.08107v1 Announce Type: cross Abstract: Multimodal expansion of large language models (LLMs) enables new perceptual capabilities but often compromises the language intelligence acquired duri
arXiv:2602.00884v2 Announce Type: replace Abstract: Neural operators have shown promise in learning solution maps of partial differential equations (PDEs), but they often struggle to generalize when t
arXiv:2608.08676v1 Announce Type: cross Abstract: Semantic vision encoders have become a central visual interface for multimodal understanding and semantic conditioning in image generation. However, t
arXiv:2608.09730v1 Announce Type: new Abstract: Vision-language-action (VLA) models are a widely adopted paradigm for embodied policies. They excel at efficient closed-loop control but do not explicit
arXiv:2608.07323v1 Announce Type: new Abstract: We test whether decoder-only language-model FFNs require SwiGLU's open positive tail. We introduce MemGLU as a closed-tail comparator derived from a mem
arXiv:2608.07436v1 Announce Type: new Abstract: Under the standard split, Muon gets hidden matrices and AdamW embeddings/output head. Muon groks modular addition faster, but its solutions do not hold.
arXiv:2608.06628v1 Announce Type: new Abstract: Diffusion language models (dLLMs) offer a promising alternative to autoregressive models by accelerating inference through parallel decoding. Recent dLL
arXiv:2608.07249v1 Announce Type: new Abstract: We introduce Stoicheia, a 405M-parameter character-level masked-diffusion encoder for Ancient Greek whose input factors into five aligned, independently
arXiv:2608.07314v1 Announce Type: cross Abstract: Vision-language-action (VLA) models are commonly adapted to downstream manipulation tasks via supervised fine-tuning (SFT) or online reinforcement lea
*SupraLabs released a new experimental model!* SupraElegans-500K is a ~500,000-parameter causal language model built around a sparse, signed, recurrent neural graph. No Transformer, no attention mecha
arXiv:2608.06161v1 Announce Type: new Abstract: Synthetic 3D scene generation is increasingly used as a data source for computer vision and embodied AI, but existing generators often optimize perceptu
arXiv:2608.05424v1 Announce Type: new Abstract: Deep vision models exploit shortcuts, relying on cues that correlate with supervision signals. Prior work has focused on visible biases, such as object-
arXiv:2608.05706v1 Announce Type: new Abstract: World models enable agents to perform forward rollout and planning without real-world interaction. However, their application in open-world embodied int