Knowledge catalogue
arXiv:2606.29845v1 Announce Type: new Abstract: Flicker-banding (FB), arises from temporal aliasing between a camera's rolling shutter and a display's brightness modulation, degrading screen-captured
arXiv:2606.28778v1 Announce Type: cross Abstract: In next-generation wireless networks, the growing density of devices and limited spectrum resources pose severe jamming challenges to fragile legitima
Building voice agents can come with tradeoffs. 💬 Better convos w/ speech to speech models Vs 🥪 More reliable harnesses w/ sandwich architecture How to build a voice research agent with both: ✅ Gemini
arXiv:2606.30609v1 Announce Type: cross Abstract: Sparse Autoencoders (SAEs) are widely used to interpret large language models by decomposing activations into sparse, human-understandable features, b
arXiv:2606.30412v1 Announce Type: cross Abstract: From housing allocation for households experiencing homelessness to triage in emergency departments, LLMs are increasingly being considered as judges
Can regularization based JEPA (e.g. SIGReg) scale and compete with SOTA foundation models (DINO)? Here is the answer: yes and with 10x less data. VISReg (slight variation of SIGReg) competes with DINO
arXiv:2606.30430v1 Announce Type: cross Abstract: The increasing connectivity of modern vehicles has made securing in-vehicle communication networks a critical challenge. Intrusion Detection Systems (
arXiv:2601.06972v2 Announce Type: replace Abstract: In speech language modeling, two architectures dominate the frontier: the Transformer and the Conformer. However, it remains unknown whether their c
arXiv:2606.29463v1 Announce Type: new Abstract: Recent advances in pathology foundation models have substantially improved patch and slide level representation learning from whole-slide images (WSIs).
arXiv:2606.29477v1 Announce Type: cross Abstract: The specification number sigma_n(f) of a Boolean threshold function f on n variables is the least number of points whose f-values determine f uniquely
arXiv:2606.29897v1 Announce Type: cross Abstract: Voice anonymization aims to protect speaker identity while preserving linguistic content and speech usability. However, most anonymization systems are
arXiv:2601.06891v2 Announce Type: replace Abstract: Contrastive Language-Image Pre-training (CLIP) relies on Vision Transformers whose attention mechanism is susceptible to spurious correlations, and
arXiv:2606.29876v1 Announce Type: cross Abstract: Modern large language models (LLMs) reach 60-70% diagnostic accuracy on complex clinical case benchmarks, but accuracy alone cannot distinguish stable
arXiv:2606.30082v1 Announce Type: new Abstract: Developing a multi-level grading model for coronary artery stenosis holds great clinical significance for the diagnosis of coronary artery disease. Howe
arXiv:2406.03367v2 Announce Type: replace Abstract: Large Language Models (LLMs) possess extensive foundational knowledge and moderate reasoning abilities, making them suitable for general task planni
arXiv:2606.28662v1 Announce Type: cross Abstract: The flatness hypothesis suggests that flatness of the loss landscape, as measured by the eigenvalues of the loss Hessian, correlates with better neura
arXiv:2409.10908v3 Announce Type: replace-cross Abstract: Recovering the underlying k-clustering of a set U of n points by asking pair-wise same-cluster queries has garnered significant interest in th
arXiv:2606.28533v1 Announce Type: cross Abstract: Sequence learning has emerged as the promising paradigm in recommendation systems, surpassing traditional Deep Learning Recommendation Models (DLRM) b
arXiv:2601.12507v2 Announce Type: replace Abstract: Low-resolution remote sensing small object detection is limited by both missing visual details and the ambiguity of how details serve detection. Exi
arXiv:2606.28696v1 Announce Type: new Abstract: Composition is a high-level visual intent that governs where subjects are placed and how a scene is organized, yet current unified multimodal models rem
arXiv:2606.29085v1 Announce Type: cross Abstract: The carbonized papyri from Herculaneum preserve the only large-scale library to survive from classical antiquity, but many unopened rolls remain unrea
arXiv:2511.08307v2 Announce Type: replace-cross Abstract: Generative models, such as large language models or text-to-image diffusion models, can generate relevant responses to user-given queries. Res
arXiv:2606.28598v1 Announce Type: cross Abstract: Prediction sets should have high coverage to be useful, but some coverage notions are more practically relevant than others. In the classification set
arXiv:2602.17393v3 Announce Type: replace Abstract: Reliable odometry for legged robots without cameras or LiDAR remains challenging due to IMU drift and noisy joint velocity sensing. This paper prese
arXiv:2606.30559v1 Announce Type: new Abstract: We characterize weakly regularized continual classification in homogeneous models as sequential projections onto task margin sets. This result generaliz
arXiv:2606.29024v1 Announce Type: new Abstract: IndicTrans2 is the strongest open English to Indic translation system, but like most systems it is trained on general text and tends to sound stiff on c
arXiv:2606.28574v1 Announce Type: cross Abstract: When a large language model (LLM) codes a construct in text as a human annotator would, that agreement makes the LLM a reliable coder. Yet reliability
arXiv:2606.30365v1 Announce Type: new Abstract: Deep Metric Learning (DML) often struggles with zero-shot generalization because standard objectives inherently capture what co-occurs rather than what
arXiv:2606.29563v1 Announce Type: cross Abstract: Large language models (LLMs) excel at complex tasks like question answering and summarization, thanks to their ability to handle long-context inputs.
arXiv:2606.29328v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) typically treats context selection as ranking chunks against a single query embedding. This assumption breaks dow
arXiv:2606.28951v1 Announce Type: new Abstract: Accurate localization of unmanned aerial vehicles (UAVs) is essential for applications such as structural health monitoring, especially in environments
arXiv:2606.29757v1 Announce Type: new Abstract: Standard stereo VIO focuses exclusively on the benefit of metric scale via single-spectrum baselines, often overlooking the risks of spectral redundancy
arXiv:2604.02948v2 Announce Type: replace Abstract: Multimodal semantic segmentation has shown great potential in leveraging complementary information across diverse sensing modalities. However, exist
arXiv:2510.09484v3 Announce Type: replace Abstract: Limited-Area Models (LAMs) enable weather forecasting over regional domains at higher resolutions than what is computationally feasible for global m
arXiv:2606.30249v1 Announce Type: cross Abstract: Detecting communities in heterophilic graphs -- where connected nodes often belong to different classes -- is hard for unsupervised methods: classical
arXiv:2606.28929v1 Announce Type: cross Abstract: Cybersecurity is a real-life test-bed for many machine learning problems at once, especially when considering modern strides in using Large Language M
arXiv:2606.28386v1 Announce Type: cross Abstract: Image autoregressive models (IARs) have recently demonstrated remarkable capabilities in visual content generation, achieving photorealistic quality a
arXiv:2606.29924v1 Announce Type: new Abstract: Generating 3D hand-object interactions is essential for applications in robotics, XR, and synthetic data generation, where flexible controllability and
arXiv:2606.28402v1 Announce Type: new Abstract: Small object segmentation in medical imaging is primarily hindered by class imbalance and inherent boundary complexity. Consequently, conventional globa
arXiv:2606.29176v1 Announce Type: new Abstract: A deep network's loss is invariant to continuous symmetries of its parameters: the logit shift, the ReLU rescaling, the LayerNorm scale, the per-head at
arXiv:2606.29324v1 Announce Type: new Abstract: Low-Earth orbit (LEO) satellite Internet has become an indispensable infrastructure that provide growing coverage for global users. Despite extensive me
arXiv:2606.28479v1 Announce Type: cross Abstract: CSIRTs increasingly fine tune language models on vulnerability scan records, but these records expose internal network topology and create privacy ris
arXiv:2606.30263v1 Announce Type: cross Abstract: Existing defenses are effective when harmful content is explicitly mixed into downstream fine-tuning data, but crafted samples can instead hide harmfu
arXiv:2602.19323v2 Announce Type: replace Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful paradigm for real-time and high-fidelity 3D reconstruction from posed images. However, recent
arXiv:2606.29223v1 Announce Type: new Abstract: Autoregressive LLM decoding evaluates every generated token through the full layer stack, even though many tokens become predictable at intermediate dep
arXiv:2606.28453v1 Announce Type: cross Abstract: Computed tomography (CT) plays a crucial role in medical diagnosis, but minimizing radiation exposure while maintaining image quality remains a critic
arXiv:2606.29718v1 Announce Type: cross Abstract: Extensive context has become the norm as Large Language Models (LLMs) are increasingly deployed in long-horizon tasks. The concern that increasing con
arXiv:2606.28417v1 Announce Type: new Abstract: Recently, diffusion models have been widely adopted in generative modeling and have served as foundational models for many image generation tasks. To co
arXiv:2606.06179v2 Announce Type: replace-cross Abstract: Score-based diffusion models are typically trained by minimizing the L^2 score matching error, and standard theoretical analyses rely on this
arXiv:2601.04860v2 Announce Type: replace Abstract: Interactive 3D segmentation of a reconstructed scene should not require a representation-specific optimization loop. We observe that the recipe for
arXiv:2606.29614v1 Announce Type: cross Abstract: This study examines whether supervised fine-tuning remains necessary for Turkish sentiment analysis in the era of large language models. We compare cl
arXiv:2606.29613v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures have recently been extended with role-based mechanisms for interpretability. This is typically done by assignin
arXiv:2606.30500v1 Announce Type: cross Abstract: We propose doubly robust adaptive conformal inference (DR-ACI), which constructs prediction intervals for doubly robust pseudo-outcomes under temporal
arXiv:2603.28049v3 Announce Type: replace Abstract: Autoregressive (AR)-Diffusion hybrid paradigms combine AR's structured semantic modeling with diffusion's high-fidelity synthesis, yet suffer from a
arXiv:2602.02969v2 Announce Type: replace Abstract: Infrared small targets are typically tiny and locally salient, which belong to high-frequency components (HFCs) in images. Single-frame infrared sma
arXiv:2606.30557v1 Announce Type: new Abstract: DiT video generation is latency-intensive due to iterative full-frame denoising, while prior cloud-edge methods largely rely on static inter-step decoup
arXiv:2606.30093v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) mitigates hallucinations in Large Language Models (LLMs) by grounding the generation process on external knowledge.
arXiv:2606.30215v1 Announce Type: cross Abstract: RGB-T detectors leverage the complementary strengths of visible and thermal infrared modalities, achieving robust performance under challenging condit
arXiv:2507.04771v2 Announce Type: replace-cross Abstract: Privacy protection laws, such as the GDPR, grant individuals the right to request the forgetting of their personal data not only from database
arXiv:2509.12159v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models have demonstrated exceptional performance in UI2Code tasks, significantly enhancing website development effic