Knowledge catalogue
arXiv:2605.06173v2 Announce Type: replace-cross Abstract: Diabetic Retinopathy (DR) is a leading cause of preventable blindness among working-age adults worldwide, yet most automated screening systems
arXiv:2605.07186v1 Announce Type: cross Abstract: Existing Large Language Model (LLM) benchmarks primarily focus on syntactically correct inputs, leaving a significant gap in evaluation on imperfect t
arXiv:2605.00957v1 Announce Type: cross Abstract: Achieving the right amount of trust in AI systems is important, but challenging. The problem is exacerbated with the rise of Large Language Models (LL
arXiv:2605.01163v1 Announce Type: cross Abstract: Shared embedding spaces are widely used for multimodal search and data curation. In practice, two problems often limit how well this works. First, emb
arXiv:2604.25924v1 Announce Type: cross Abstract: Large Language Models have been increasingly employed in the creation of Virtual Assistants due to their ability to generate human-like text and handl
arXiv:2604.05190v2 Announce Type: replace-cross Abstract: Screening patients for enrollment is a well-known, labor-intensive bottleneck that leads to under-enrollment and, ultimately, trial failures.
arXiv:2604.21229v1 Announce Type: cross Abstract: Large language model assistants are increasingly expected to retain and reason over information accumulated across many sessions. We introduce Engrama
arXiv:2604.20623v1 Announce Type: cross Abstract: Traditional change detection identifies where changes occur, but does not explain what changed in natural language. Existing remote sensing change cap
arXiv:2511.02356v2 Announce Type: replace-cross Abstract: Despite extensive safety alignment, Large Language Models (LLMs) remain vulnerable to jailbreak attacks. However, existing methods generally l
arXiv:2601.17230v2 Announce Type: replace Abstract: Automated Fact-Checking has largely focused on verifying general knowledge against static corpora, overlooking high-stakes domains like law where tr
arXiv:2510.15946v3 Announce Type: replace Abstract: Internet memes have emerged as a popular multimodal medium, yet they are increasingly weaponized to convey harmful opinions through subtle rhetorica
arXiv:2604.07021v2 Announce Type: replace Abstract: Weakly supervised semantic segmentation aims to achieve pixel-level predictions using image-level labels. Existing methods typically entangle semant
arXiv:2601.15170v2 Announce Type: replace Abstract: The rapid expansion of research across machine learning, vision, and language has produced a volume of publications that is increasingly difficult t
arXiv:2511.00179v2 Announce Type: replace-cross Abstract: Capturing the structural changes that molecules undergo during chemical reactions in real space and time is a long-standing dream and an essen
arXiv:2604.12498v1 Announce Type: cross Abstract: We present Lit2Vec, a reproducible workflow for constructing and validating a chemistry corpus from the Semantic Scholar Open Research Corpus using co
arXiv:2604.10898v1 Announce Type: new Abstract: Large language models (LLMs) have shown great performance on complex reasoning tasks but often require generating long intermediate thoughts before reac
Harrison Chase, co-founder of LangChain, argues that while prompt engineering is foundational and can get you 80% of the way to a functional AI system, the remaining 20% of engineering effort involves
arXiv:2604.08456v1 Announce Type: cross Abstract: Despite rapid progress, pretrained vision-language models still struggle when answers depend on tiny visual details or on combining clues spread acros
arXiv:2604.07027v1 Announce Type: new Abstract: Nonstationarity is ubiquitous in practical classification settings, leading deployed models to perform poorly even when they generalize well to holdout
arXiv:2610.19240v1 Announce Type: new Abstract: Financial disclosures express the underlying relationships of double-entry accounting through unstructured text. While financial LLM benchmarks predomin
arXiv:2610.09757v1 Announce Type: new Abstract: Mid-prefill pruning can reduce the sequence processed by deeper transformer layers, but attention concentration alone does not certify that discarded co
arXiv:2610.09375v1 Announce Type: new Abstract: Organizations increasingly use frontier language models to analyze customer feedback, but answer quality also depends on how that feedback is organized
EmbeddingGemma 2 came out this week. It maps images and text into one 768-dim space, so you can search photos by describing them. I ported its text and vision towers to ruNNtime, a WebGPU inference li
arXiv:2609.36923v1 Announce Type: new Abstract: Existing reactive Graphical User Interface (GUI) agents often fail in long-horizon, dynamic scenarios, where unexpected disturbances trigger attention-d
arXiv:2609.31698v1 Announce Type: new Abstract: Most existing MEG and EEG (M/EEG) visual decoding methods align brain signals with a single global embedding extracted from a pretrained visual encoder,
arXiv:2609.33359v1 Announce Type: new Abstract: Geometric view synthesis can expand a single wine-label photograph into a training set, but its value with pretrained image encoders is unclear. We stud
arXiv:2609.26567v1 Announce Type: new Abstract: Robots that store past experiences must select which one to reuse in a new scene. Most systems select by visual similarity, and most evaluations report
arXiv:2609.22770v2 Announce Type: cross Abstract: We study a parameterized hybrid ranker that fuses a dense embedding list and a sparse lexical list. The method has a small, explicit parameter vector:
arXiv:2609.19855v1 Announce Type: cross Abstract: Geographic applications need every object inside a radius that satisfies a semantic threshold, yet embedding indexes return approximate top-ranked lis
arXiv:2608.22457v1 Announce Type: new Abstract: An inner hood panel must meet a deflection target, stay below a stress limit, and hit a mass target. Machine-learned surrogates have made the forward di
arXiv:2608.22516v1 Announce Type: cross Abstract: A long-video answer is evidence-supported only when the frames decoded from the video cover every event the answer depends on. Existing evaluations sc
arXiv:2608.20326v1 Announce Type: cross Abstract: Deep neural networks are often overconfident, assigning high confidence even to incorrect predictions. Consequently, users lack a reliable signal for
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:2608.12282v1 Announce Type: new Abstract: Agents deployed in enterprise settings must reason across structured APIs and document collections, yet existing benchmarks evaluate these capabilities
arXiv:2608.05171v1 Announce Type: cross Abstract: Generative AI (GAI) creates new opportunities for collaborative problem-solving (CPS), yet its role in shaping student interaction remains unclear. To
arXiv:2608.03228v1 Announce Type: new Abstract: Existing low rank KV cache methods preserve either model weights or key variance, neither of which directly reflects the attention scores used during in
arXiv:2607.23295v1 Announce Type: cross Abstract: In real-world machine learning applications, incomplete observations create a fundamental challenge. Researchers have come up with several ideas to ad
arXiv:2607.19747v1 Announce Type: new Abstract: As large language models and AI agents become the primary consumers of search results, document set quality determines the upper bound of downstream gen
arXiv:2601.02023v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) increasingly utilize massive context windows as working memory for autonomous tasks, their reliability fluctua
arXiv:2607.07144v1 Announce Type: new Abstract: The key-value (KV) cache dominates the memory cost of long-context autoregressive inference, and a growing body of work compresses it through quantizati
arXiv:2607.06283v1 Announce Type: new Abstract: Skill usage can significantly enhance the ability of modern agent systems to complete complex tasks. However, the growing scale of skill libraries makes
arXiv:2602.19127v2 Announce Type: replace Abstract: With the rapid advancement of agent-based methods in recent years, Agentic RAG has undoubtedly become an important research direction. Multi-hop rea
arXiv:2607.02371v1 Announce Type: cross Abstract: Over 285 million people worldwide live with a visual impairment, for whom everyday tasks such as avoiding obstacles, locating personal belongings, rec
arXiv:2509.15026v2 Announce Type: replace-cross Abstract: We seek to recover an unknown signal from nonlinear amplitude-only measurements, a challenging inverse problem. Strong theoretical guarantees
arXiv:2607.00016v1 Announce Type: cross Abstract: Information localization within massive repositories is a cornerstone of agentic LLM systems. While synthetic data-driven optimization has proven succ
arXiv:2606.26807v1 Announce Type: new Abstract: We propose a new method that allows an LLM to automatically pull in factual knowledge from a knowledge base during token generation. This means that (1)
arXiv:2606.21633v1 Announce Type: new Abstract: Diffusion LLMs (dLLMs) improve GPU utilization over autoregressive decoding by generating multiple tokens per forward pass, but their KV cache still gro
arXiv:2601.21218v2 Announce Type: replace Abstract: Large language models (LLMs) are highly capable of answering questions, but they are often unaware of their own knowledge boundary, i.e., knowing wh
arXiv:2510.13272v3 Announce Type: replace Abstract: Inspired by the success of reinforcement learning (RL) in Large Language Model (LLM) training for domains like math and code, recent work has begun
arXiv:2503.06473v5 Announce Type: replace-cross Abstract: Growing evidence suggests that layer attention mechanisms, which enhance interaction among layers in deep neural networks, have significantly
arXiv:2508.01815v2 Announce Type: replace-cross Abstract: Text-to-SPARQL maps natural-language questions to executable SPARQL queries over RDF knowledge graphs. While standard evaluations often fix th
arXiv:2605.27440v1 Announce Type: cross Abstract: Small changes to how a buyer phrases a question -- 'best CRM' vs 'top CRM' vs 'best CRM for a SaaS startup' -- produce substantially different brand r
arXiv:2605.24534v1 Announce Type: new Abstract: We present a fully automated pipeline that transforms large collections of court decisions into legal commentaries for statutes - without providing any
arXiv:2605.22850v1 Announce Type: cross Abstract: Prefix KV caching has become a key mechanism in LLM serving: it reduces time to first token (TTFT) by avoiding redundant computation across requests t
arXiv:2605.22041v1 Announce Type: cross Abstract: While RAG systems are increasingly deployed in dynamic web search, temporal volatility amplifies their vulnerability to adversarial attacks. Existing
arXiv:2407.20595v4 Announce Type: replace-cross Abstract: Deciding whether two pieces of text share an author is made difficult by topical confound: two writers covering the same topic often look more
arXiv:2605.17034v1 Announce Type: cross Abstract: Standard PII filters often miss contextual data leakage in RAG systems, such as non-regulated attribute clusters that collectively identify individual
arXiv:2511.21247v2 Announce Type: replace-cross Abstract: This paper introduces The Spheres dataset, multitrack orchestral recordings designed to advance machine learning research in music source sepa
arXiv:2605.11374v1 Announce Type: cross Abstract: Test-time compute is widely believed to benefit only large reasoning models. We show it also helps small embedding models. Most modern embedding check
arXiv:2604.22760v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly operate as autonomous agents that reason over external APIs to perform complex tasks. However, their reliabi