Knowledge catalogue
arXiv:2605.18032v1 Announce Type: cross Abstract: Multi-agent LLM workflows -- systems composed of multiple role-specific LLM calls -- often outperform single-prompt baselines, but they remain difficu
arXiv:2602.21426v2 Announce Type: replace Abstract: We consider the problem of sampling from a posterior distribution arising in Bayesian inverse problems in science, engineering, and imaging. Our met
arXiv:2605.17679v1 Announce Type: cross Abstract: Cancer survivors face elevated rates of depression, anxiety, and general emotional distress, yet the precise moments they most need support are often
arXiv:2605.16535v1 Announce Type: cross Abstract: Industrial multi-label document understanding pipelines score candidate labels and threshold or rank them to form a label set per document. This early
arXiv:2605.16874v1 Announce Type: new Abstract: Large reasoning models (LRMs) substantially outperform their base LLM counterparts on challenging reasoning benchmarks, yet it remains poorly understood
arXiv:2303.11675v3 Announce Type: replace Abstract: R}easoning for Robust Human Pose and Shape Estimation), designed to estimate human body shape and pose from single-view images. ReBaR effectively ad
arXiv:2605.17967v1 Announce Type: new Abstract: This paper explores a scientific question in supervised fine-tuning (SFT): why SFT is broadly effective for small-scale deep neural networks, yet can pr
arXiv:2605.18599v1 Announce Type: new Abstract: Transformer-based models have advanced feedforward novel view synthesis (NVS). Current architectures such as GS-LRM and LVSM mix semantic information (e
arXiv:2601.03851v2 Announce Type: replace Abstract: Table Question Answering (TableQA) benefits significantly from table pruning, which extracts compact sub-tables by eliminating redundant cells to st
arXiv:2605.16981v1 Announce Type: new Abstract: Streaming 3D reconstruction under a strict constant-memory budget hinges on how the recurrent state is updated as the stream evolves. We profile TTT3R-s
arXiv:2605.16767v1 Announce Type: new Abstract: Multi-label legal annotation requires assigning multiple labels from large, evolving taxonomies to long, fact-intensive documents, often under limited s
arXiv:2605.17279v1 Announce Type: cross Abstract: Code merging is a significant challenge, particularly in large-scale projects. Existing solutions, including program analysis and machine learning, sh
arXiv:2605.17985v1 Announce Type: cross Abstract: We propose a new method for compressing physics foundation models (PFMs) which is a new trend in AI for Science. While model compression is essential
arXiv:2605.18104v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) often fail to transfer safety capabilities learned in the text modality to semantically equivalent non-text inp
arXiv:2510.26635v3 Announce Type: replace-cross Abstract: Summary: SAMRI is an MRI-specialized adaptation of the Segment Anything Model achieving superior whole-body MRI segmentation, particularly for
arXiv:2605.16686v1 Announce Type: new Abstract: Knowledge editing (KE) provides a lightweight alternative to repeated fine-tuning of LLMs. However, most existing KE methods target dense feed-forward l
arXiv:2605.16412v1 Announce Type: cross Abstract: Despite the central role of action in embodied intelligence, learning transferable action representations from visual transitions remains a fundamenta
arXiv:2605.16883v1 Announce Type: new Abstract: Autonomous Graphical User Interface (GUI) agents often struggle with multi-step tasks due to constrained context windows and static policies that fail t
arXiv:2605.18018v1 Announce Type: cross Abstract: We present SWIM (See What I Mean), a novel training strategy that aligns vision and language representations to enable fine-grained object understandi
arXiv:2605.17630v1 Announce Type: new Abstract: Here's a trimmed version under 1920 characters: Open-vocabulary segmentation models such as SAM3 achieve strong performance through concept-level text p
arXiv:2603.02218v2 Announce Type: replace-cross Abstract: Large language models (LLMs) make it plausible to build systems that improve through self-evolving loops, but many existing proposals are bett
arXiv:2602.08167v2 Announce Type: replace-cross Abstract: Embodied Chain-of-Thought (CoT) reasoning has significantly enhanced Vision-Language-Action (VLA) models, yet current methods rely on rigid te
arXiv:2605.18039v1 Announce Type: new Abstract: Learning dense correspondences across deformable 3D shapes remains a long-standing challenge due to structural variability, non-isometric deformation, a
arXiv:2605.16973v1 Announce Type: new Abstract: Domain generalization aims to enhance model robustness against unseen domains with embedding distribution shifts. While large-scale vision-language mode
arXiv:2605.16565v1 Announce Type: new Abstract: Skim is a speculative execution framework for web agents that exploits the predictable structure of purpose-built websites. Today's web-agent expense is
arXiv:2605.17672v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) achieve strong performance by generating long chains of thought (CoT), but often overthink, continuing to reason after a s
arXiv:2605.16398v1 Announce Type: cross Abstract: Contact-rich robot dynamics are hybrid: a single observation can match several latent states and contact regimes (free, impact, stick--slip). A standa
arXiv:2605.17762v1 Announce Type: new Abstract: Music search at the scale of Amazon Music presents a unique challenge: queries frequently deviate from indexed metadata due to misspellings, transpositi
arXiv:2505.17674v2 Announce Type: replace Abstract: Spiking Neural Networks (SNNs) provide an energy-efficient way to extract 3D spatio-temporal features. However, existing SNNs still exhibit a signif
arXiv:2605.17577v1 Announce Type: new Abstract: Large-scale pre-trained Vision-Language models (VLMs), such as CLIP, exhibit strong zero-shot generalization, yet remain highly vulnerable to impercepti
arXiv:2605.16891v1 Announce Type: new Abstract: We introduce a tensor-channel equivariant graph neural network for direct prediction of molecular polarizability tensors. Building on the efficient PaiN
arXiv:2605.17500v1 Announce Type: cross Abstract: Generative text-to-image models are typically trained on large-scale web-scraped datasets that include diverse visual content such as copyrighted and
arXiv:2605.18177v1 Announce Type: new Abstract: Query-based Vision Transformer segmentation models typically reconstruct dense spatial feature maps to predict masks, inheriting design patterns from co
arXiv:2605.17217v1 Announce Type: cross Abstract: Marine oil spills require rapid detection to mitigate severe ecological and economic damage. While satellite-based Synthetic Aperture Radar (SAR) prov
arXiv:2605.17994v1 Announce Type: cross Abstract: New item growth is critical for maintaining a healthy ecosystem in large-scale e-commerce platforms. However, existing systems tend to prioritize pres
arXiv:2512.11089v4 Announce Type: replace-cross Abstract: We introduce test prediction variance (TPV)--the first-order sensitivity of a trained model's outputs to parameter perturbations--as a unifyin
arXiv:2605.18163v1 Announce Type: new Abstract: Hallucination correction is not a one-direction problem. We show that intermediate layers are neither uniformly more truthful than final layers nor unif
arXiv:2605.16810v1 Announce Type: new Abstract: We present a training-free framework for occluded text rendering with a pretrained FLUX.1-dev backbone. The task requires a model to render recognizable
arXiv:2605.16735v1 Announce Type: cross Abstract: The deployment of 5G Multicast-Broadcast Services (MBS) is emerging as a critical technology for spectral-efficient UHD content delivery and serving a
arXiv:2605.16638v1 Announce Type: new Abstract: Recent research has demonstrated that Universal Multimodal Embedding (UME) benefits significantly from Chain-of-Thought (CoT) reasoning. In this paradig
arXiv:2601.12696v2 Announce Type: replace Abstract: Current guardian models are predominantly Western-centric and optimized for high-resource languages, leaving low-resource African languages vulnerab
arXiv:2605.17575v1 Announce Type: cross Abstract: Network traffic classification (NTC) models often suffer severe performance degradation when deployed in real-world environments due to distribution s
arXiv:2603.02667v2 Announce Type: replace Abstract: Unifying text-image contrastive learning and text-to-image (T2I) generation in a single end-to-end model is challenging because the two objectives d
arXiv:2401.03717v4 Announce Type: replace-cross Abstract: Time-series data exists in every corner of real-world systems and services, ranging from satellites in the sky to wearable devices on human bo
arXiv:2304.10726v3 Announce Type: replace-cross Abstract: We introduce the Deep Learning Vulnerability Analyzer (DLVA) for Ethereum smart contracts based on neural networks. We train DLVA to judge byt
v0.30.0-rc21 is a pre-release version that changes Ollama's architecture to directly support llama.cpp instead of building on top of GGML, enabling GGUF file format compatibility. MLX is used to accel
arXiv:2510.06809v3 Announce Type: replace Abstract: Echocardiography is a critical tool for detecting heart diseases, yet its steep operational difficulty causes a shortage of skilled personnel. Probe
arXiv:2605.17605v1 Announce Type: new Abstract: Modern generative modeling has grown into a broad collection of related but often separately implemented paradigms, including denoising diffusion models
arXiv:2605.17626v1 Announce Type: new Abstract: Test-time scaling is an important mechanism for improving large language models, especially on tasks with deterministic verifiers. Code translation is a
arXiv:2605.17467v1 Announce Type: new Abstract: Large language model-driven multi-agent systems (LLM-MAS) excel at complex tasks, yet unreliable agents remain a key bottleneck to system-level reliabil
arXiv:2605.16859v1 Announce Type: cross Abstract: 3D change detection from multi-view images is essential for urban monitoring, disaster assessment, and autonomous driving. However, existing methods p
arXiv:2605.16911v1 Announce Type: new Abstract: 3D semantic occupancy prediction requires accurate 2D-to-3D feature lifting, yet current methods restrict camera geometry to initial projections. Subseq
arXiv:2602.07272v2 Announce Type: replace Abstract: Creating photorealistic materials for 3D rendering requires exceptional artistic skill. Generative models for materials could help, but are currentl
arXiv:2605.18390v1 Announce Type: new Abstract: In this work, we explore the largely unexplored direction of building a generalist image tokenizer directly on top of a frozen vision foundation model (
arXiv:2605.18740v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) still struggle with fine-grained visual understanding, where answers often depend on small but decisive evide
We are releasing Carbon: a crazy fast DNA model Carbon is 275x faster than the next best model. So fast you can process the whole human genome on a single GPU in <2 days. Here are the tricks we used:
arXiv:2509.22510v3 Announce Type: replace Abstract: Alignment of Large Language Models (LLMs) is the ability to satisfy desired objectives during generation, which is critical for trustworthy deployme
arXiv:2605.17658v1 Announce Type: new Abstract: Different age-related regulations have been proposed to protect minors from harmful content and interactions online. Automated age estimation is central
arXiv:2603.17041v2 Announce Type: replace-cross Abstract: Generative models are increasingly deployed as substitutes for real data in downstream scientific workflows, yet standard evaluation criteria
arXiv:2601.17887v2 Announce Type: replace Abstract: Long-term memory enables large language model (LLM) agents to support personalized and sustained interactions. However, most work on personalized ag