Knowledge catalogue
arXiv:2609.22510v1 Announce Type: cross Abstract: As LLM applications integrate with external tools, they are increasingly exposed to indirect prompt injection (IPI), where adversarial instructions ar
arXiv:2609.22926v1 Announce Type: new Abstract: Reach-and-attach of soft robotic arms with passive suction requires accurate targeting and sufficient contact speed, yet geared actuators can impose a s
arXiv:2609.24057v1 Announce Type: cross Abstract: Medical image interpretation is central to diagnosis and care, yet adapting general-purpose multimodal large language models (MLLMs) often requires re
arXiv:2609.22988v1 Announce Type: new Abstract: Multilingual code language models transfer skills across programming languages (PLs), but whether any PL occupies a privileged pivot position remains co
arXiv:2609.22218v1 Announce Type: cross Abstract: As LLM agents are exposed to hundreds to tens of thousands of skills, tools, and API functions, full-library prompting becomes costly, slow, and less
arXiv:2607.18840v2 Announce Type: replace Abstract: World Action Models (WAMs) offer a promising paradigm for robotic manipulation by jointly modeling visual state transitions and robot actions. Howev
arXiv:2609.21378v1 Announce Type: new Abstract: Reinforcement learning has substantially improved large language model (LLM) agents in verifiable domains, but remains difficult to apply to open-ended
arXiv:2609.20974v1 Announce Type: new Abstract: In Mixture-of-Experts language models, the router typically selects and weights experts based on the token's hidden state, utilizing limited contextual
arXiv:2609.20888v1 Announce Type: new Abstract: Massive KV caches can cause severe memory-bandwidth bottlenecks during long-context decoding. Sparse attention methods mitigate this via selective loadi
arXiv:2609.21533v1 Announce Type: new Abstract: LLM-based multi-agent systems generate collaboration traces that record how agents plan tasks, verify intermediate results, and repair failures. Reusing
arXiv:2609.21468v1 Announce Type: new Abstract: This paper studies agentic image restoration, in which multimodal agents coordinate specialized restoration tools to recover images affected by complex
arXiv:2609.21425v1 Announce Type: new Abstract: Zero-shot time-series forecasting (TSF) is often described as forecasting without target-specific parameter updates, but that training-status condition
Inference scaling part 1. Starting with a modded text generation function (temperature scaling, top-p filtering, multinomial sampling) to generate diverse outputs for self-consistency and best-of-N (i
arXiv:2609.20508v1 Announce Type: new Abstract: E-commerce livestreams have emerged as an important channel for presenting products to online consumers, containing multiple products whose information
arXiv:2609.19775v1 Announce Type: new Abstract: Published medical case reports serve as a crucial medical information carrier, documenting discoveries in rare diseases, diagnostic methods, and innovat
arXiv:2609.19569v1 Announce Type: cross Abstract: Disease severity classification for genetic conditions is subjective and labor-intensive, creating bottlenecks in genomic screening, where commercial
arXiv:2609.20630v1 Announce Type: new Abstract: Search advertising connects user intent with commercial content and plays a critical role in platform monetization. Recent systems typically align pretr
A database knows where your data is. A vector database understands what your data means. It finds information based on similarity and meaning, not just exact keywords, powering semantic search, RAG, r
arXiv:2609.18204v1 Announce Type: cross Abstract: Organizations increasingly use oversight loops where one large language model (LLM) audits another's outputs alongside procedural traces of claimed st
arXiv:2609.19128v1 Announce Type: new Abstract: Language agents remain brittle in interactive environments, where success requires long-horizon state tracking, valid action execution, and recovery fro
arXiv:2609.17883v1 Announce Type: cross Abstract: The rapid adoption of generative AI has made final artifacts unreliable evidence of student learning, and AI detectors that examine only the finished
arXiv:2512.07179v2 Announce Type: replace Abstract: Intelligent Tutoring Systems (ITS) provide personalized learning paths by diagnosing learners' proficiency. Knowledge Tracing (KT) models play a cen
arXiv:2609.18852v1 Announce Type: new Abstract: Longitudinal electronic health records (EHRs) capture years of patient history across notes, codes, labs, and procedures, and contain evidence needed to
arXiv:2609.18011v1 Announce Type: new Abstract: In collaborative tasks with asymmetric information, participants coordinate their understanding through interaction. We ask whether gaze provides eviden
arXiv:2602.02888v2 Announce Type: replace-cross Abstract: Hallucinations remain a major obstacle for large language models (LLMs), especially in safety-critical domains. We present HALT (Hallucination
arXiv:2609.17764v1 Announce Type: new Abstract: Attention-based rerankers score documents by aggregating query-to-document attention and subtracting a null-query calibration pass to remove positional
arXiv:2609.17757v1 Announce Type: new Abstract: Behavioral cloning trains a policy offline on expert demonstrations, but deployment is closed loop: each action affects the observations the policy rece
arXiv:2609.18842v1 Announce Type: new Abstract: The scaling laws hold that a language model grows more capable with more parameters and more training data, and Mixture-of-Experts (MoE) architectures h
arXiv:2006.12694v2 Announce Type: replace-cross Abstract: Transfer learning involves taking information and insight from one problem domain and applying it to a new problem domain. Although widely use
arXiv:2609.17888v1 Announce Type: cross Abstract: We study the problem of demonstration selection, which involves selecting a subset of examples for prepending to a query to a language model. This pro
arXiv:2609.17868v1 Announce Type: new Abstract: Pathology vision-language models are commonly built by pretraining or fine-tuning large encoders on paired image-caption data. We asked whether a pathol
arXiv:2609.17631v1 Announce Type: new Abstract: AI-assisted claims can appear authoritative when evidence, analysis, human authorization, presentation, and correction history refer to different states
arXiv:2603.27526v2 Announce Type: replace Abstract: Protein fitness optimization is a discrete search problem, and the representation used for prediction also determines the neighborhood graph travers
arXiv:2609.18092v1 Announce Type: new Abstract: Global localization with scanning millimeter-wave radar remains challenging because place-recognition descriptors often discard spatial structure needed
arXiv:2609.18442v1 Announce Type: new Abstract: Safe motion planning in automated driving requires anticipating evolving traffic risks and deciding when to revise the current planned trajectory. We in
arXiv:2609.19134v1 Announce Type: new Abstract: Scientific code repositories encode decades of human knowledge in executable models, methods, and tools. Yet fragmented toolchains, implicit domain conv
arXiv:2603.14005v2 Announce Type: replace Abstract: To generalize deepfake detectors to future unseen forgeries, most existing methods attempt to simulate the dynamically evolving forgery types using
arXiv:2609.18958v1 Announce Type: cross Abstract: The natural way to review a long recording or document with a multimodal model is to hand it the raw source and ask for a review in one call. We show
arXiv:2609.18341v1 Announce Type: cross Abstract: When someone asks an AI assistant which doctor to see or which firm to trust with their savings, the answer is a referral. We audit AI provider recomm
arXiv:2609.16102v1 Announce Type: cross Abstract: Credit-risk models are trained on proxy labels and deployed under temporal and segment change, yet no single transfer metric separates base-rate shift
arXiv:2609.16496v1 Announce Type: cross Abstract: AI policies introduced by software organisations to mitigate LLM-related risks such as sensitive information leaks and unauthorised usage are not usef
arXiv:2609.16183v1 Announce Type: cross Abstract: Fixed-state recurrences--linear attention and state-space models--are reported to lag behind attention on associative recall, but whole-architecture c
arXiv:2501.09166v2 Announce Type: replace-cross Abstract: Pretrained Transformers keep what they learned in their weights and lose what they observe once a session ends. The first version of this pape
arXiv:2609.16814v1 Announce Type: new Abstract: While Large Language Model (LLM)-based Natural Language Inference (NLI) systems achieve high accuracy, their decision-making processes lack auditable st
arXiv:2604.05012v2 Announce Type: replace-cross Abstract: Efficient inference with Large Language Models (LLMs) increasingly relies on Key-Value (KV) caches to store previously computed key and value
arXiv:2609.16517v1 Announce Type: cross Abstract: Resume screeners must infer job-relevant competence from resumes whose presentation can vary substantially in wording, structure, stylistic polish, an
arXiv:2609.17008v1 Announce Type: new Abstract: Large language model (LLM) inference is often constrained by both computation and memory, especially in offloading-based deployments where model weights
arXiv:2609.16739v1 Announce Type: new Abstract: Background: Large language models (LLMs) have achieved physician-comparable performance on multiple-choice medical knowledge examinations, but their cap
arXiv:2609.17475v1 Announce Type: new Abstract: Capable open-weight models make local coding and reasoning attractive, but their context and execution state strain laptop memory. We present JustFit, a
arXiv:2609.16730v1 Announce Type: new Abstract: Conversational memory changes during use, so endpoint question answering alone cannot establish how a persistent state accumulates, ages, or incorporate
arXiv:2606.18960v3 Announce Type: replace Abstract: Action-conditioned world models have emerged as a promising paradigm for robot learning, offering a scalable alternative to costly real-world experi
Mem0 provides persistent user memory and agent memory; its vendor describes fact extraction, contradiction handling and relevant recall.
arXiv:2603.11515v2 Announce Type: replace Abstract: Today's scientific challenges, from climate modeling to Inertial Confinement Fusion design to novel material design, require exploring huge design s
arXiv:2609.15999v1 Announce Type: new Abstract: Accessing legal information in Nepal is difficult due to complex terminology, limited resources, and misinformation. We introduce an AI-powered legal as
arXiv:2609.16527v1 Announce Type: cross Abstract: Exploring the chemical space of flexible molecules remains challenging because the vast number of possible compounds and conformations, together with
arXiv:2602.03344v2 Announce Type: replace-cross Abstract: Robustness is widely viewed as a key challenge for real-world applications. However, because current research focuses only on difficult tasks,
arXiv:2609.16145v1 Announce Type: new Abstract: We study a practical question: can a small correction module fix errors in a frozen language model's outputs without degrading its base capabilities? We
arXiv:2509.07801v5 Announce Type: replace Abstract: Structured information extraction from scientific literature is crucial for capturing core concepts and emerging trends in specialized fields. While
arXiv:2609.16268v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly interleave natural language reasoning with external tools such as web search and code execution. These to
arXiv:2609.14419v1 Announce Type: cross Abstract: Person re-identification (ReID) is essential for multi-camera surveillance and tracking, yet remains difficult due to viewpoint and illumination chang