Knowledge catalogue
arXiv:2606.11199v1 Announce Type: cross Abstract: We present NightFeats, a structured multi-agent retrieval-augmented generation (RAG) system submitted to the MMU-RAGent competition at NeurIPS 2025, w
arXiv:2606.12125v1 Announce Type: new Abstract: Long-video understanding remains challenging for multimodal large language models, because temporally extended videos often contain thousands of frames
arXiv:2606.11316v1 Announce Type: new Abstract: Large language models are increasingly deployed across professional domains, bringing hard-to-predict risks, including the generation of harmful or disr
arXiv:2606.10061v1 Announce Type: new Abstract: Large language models (LLMs) increasingly participate in emotionally sensitive social conversations, where responses may shift from balanced support tow
arXiv:2606.10902v1 Announce Type: cross Abstract: Subject Customization is a foundational task in modern image generation. By providing a few reference images and a text prompt, users can generate ima
arXiv:2606.10804v1 Announce Type: new Abstract: Controlled character animation requires transferring motion from a driving sequence to a reference character. Prior works heavily rely on intermediate r
arXiv:2606.09802v1 Announce Type: cross Abstract: We consider a variant of the linear contextual stochastic multi-armed bandits, where the learner must provide recommendations to a group of users, eac
arXiv:2602.17911v3 Announce Type: replace-cross Abstract: Current biomedical question answering (QA) systems often assume that medical knowledge applies uniformly, yet real-world clinical reasoning is
arXiv:2606.08535v1 Announce Type: new Abstract: Remote sensing applications for environmental monitoring and disaster management are frequently constrained by a spatial--temporal trade-off: imagery wi
arXiv:2606.08446v1 Announce Type: cross Abstract: Despite being powerful, reinforcement learning with verifiable rewards (RLVR) induces extremely long COT, making it computationally expensive. Since R
arXiv:2606.09204v1 Announce Type: new Abstract: We present a reproducible failure mode of safety training in RAG-based LLM recommendation -- the Injection Paradox -- in which prompt injections embedde
arXiv:2606.07175v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have raised new privacy challenges. On the data side, user-provided inputs often include unpredictable sensitiv
arXiv:2606.06458v1 Announce Type: cross Abstract: Multiple Instance Learning (MIL) addresses problems where supervision is available at the level of bags of instances and has been successfully applied
arXiv:2606.05042v1 Announce Type: cross Abstract: Marginal inference in discrete graphical models forces a choice between exactness and scalability: exact algorithms are intractable for high-treewidth
arXiv:2606.04269v1 Announce Type: cross Abstract: Deformable object manipulation (DOM) is challenging due to high-dimensional, partially observable states that evolve through long-horizon, topology-ch
arXiv:2606.04320v1 Announce Type: cross Abstract: Relational Foundation Models (RFMs) promise a single pre-trained predictor that, given any relational database, returns predictions in one forward pas
arXiv:2606.03618v1 Announce Type: new Abstract: AI-assisted coding agents are bottlenecked by input-token cost. Two pathologies of raw human input drive much of this overhead: tokenization inefficienc
arXiv:2510.15780v2 Announce Type: replace-cross Abstract: Artificial intelligence (AI) is increasingly used to support renewable energy forecasting and grid operations. As renewable penetration grows,
arXiv:2606.03363v1 Announce Type: new Abstract: Text-to-SQL enables natural language access to databases, and recent LLMs have substantially advanced its capabilities. Existing benchmarks such as Spid
arXiv:2606.03197v1 Announce Type: new Abstract: Memory is an indispensable capability for long-horizon LLM agents, enabling them to preserve and utilize information accumulated across extended interac
arXiv:2503.15639v2 Announce Type: replace-cross Abstract: Modern scene text recognition systems often depend on large end-to-end architectures that require extensive training and are prohibitively exp
arXiv:2606.01134v1 Announce Type: cross Abstract: Automatically distinguishing child-directed speech from adult-directed speech in long-form recordings is key to scalable analyses of children's langua
arXiv:2602.06065v3 Announce Type: replace-cross Abstract: Understanding how the structure of language can be learned from sentences alone is a central question in both cognitive science and machine le
arXiv:2606.01072v1 Announce Type: cross Abstract: Imitation learning enables robots to learn how to execute tasks via observation. However, real-world environments like homes and offices are often sev
arXiv:2601.16462v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) has become a dominant paradigm for mitigating hallucinations in Large Language Models (LLMs) by incorporating e
arXiv:2606.02404v1 Announce Type: new Abstract: Frontier model evaluations are shifting from foundational capabilities (e.g., instruction following and reasoning) toward compositional, agentic ones, b
arXiv:2510.12624v2 Announce Type: replace-cross Abstract: Active feature acquisition (AFA) is a sequential decision-making problem where the goal is to improve model performance for test instances by
arXiv:2606.01563v1 Announce Type: new Abstract: Autoregressive decoding in Transformer-based language models relies on the KV cache, whose memory footprint grows linearly with sequence length and beco
arXiv:2606.00299v1 Announce Type: cross Abstract: While Video Diffusion Models (VDMs) excel at synthesizing high-fidelity videos, enabling precise camera and scene control remains challenging. Existin
Fine-tuning isn't dead, but the way most teams iterate on AI products has split in two. A tiny fraction run continuous RL against their own environments; everyone else has moved the iteration loop out
arXiv:2606.00704v1 Announce Type: new Abstract: Real-world image super-resolution (Real-ISR) requires balancing structural fidelity to degraded observations with realistic detail synthesis. However, e
arXiv:2606.01999v1 Announce Type: cross Abstract: Modern deep learning models for forecasting groups of time series rely on increasingly longer observation windows. However, the benefit of increasing
arXiv:2605.30510v1 Announce Type: cross Abstract: Brain cancer's severity necessitates precise brain tumor segmentation, which is crucial for effective brain tumor diagnosis. Manual identification, bu
arXiv:2605.31146v1 Announce Type: cross Abstract: This paper investigates how User Experience Research (UXR) methods can be combined with AI-supported analysis to develop clearer design direction for
arXiv:2605.31513v1 Announce Type: new Abstract: Large vision-language models (LVLMs) have demonstrated strong general multimodal capability and are increasingly deployed in downstream systems. This tr
arXiv:2506.14842v2 Announce Type: replace-cross Abstract: Building image classification models remains cumbersome in data-scarce domains, where collecting large labeled datasets is impractical. In-con
arXiv:2602.06161v2 Announce Type: replace-cross Abstract: Parallel diffusion decoding can accelerate diffusion language model inference by unmasking multiple tokens per step, but aggressive parallelis
arXiv:2510.20743v2 Announce Type: replace-cross Abstract: We present Empathic Prompting, a novel framework for multimodal human-AI interaction that enriches Large Language Model (LLM) conversations wi
arXiv:2509.21190v4 Announce Type: replace-cross Abstract: Time series anomaly detection (TSAD) is a critical task, but developing models that generalize to unseen data in a zero-shot manner remains a
arXiv:2605.28508v1 Announce Type: new Abstract: Existing AI evaluation practices often fail to capture how systems actually perform in low-resource environments, where operational constraints shape us
arXiv:2604.00402v2 Announce Type: replace-cross Abstract: Developing robust models to accurately predict the trajectories of surrounding agents is fundamental to autonomous driving safety. However, mo
arXiv:2510.17620v2 Announce Type: replace Abstract: Large language models may encode sensitive information or outdated knowledge that needs to be removed, to ensure responsible and compliant model res
arXiv:2512.23959v3 Announce Type: replace-cross Abstract: Multi-step retrieval-augmented generation (RAG) has become a widely adopted strategy for enhancing large language models (LLMs) on tasks that
arXiv:2605.28116v1 Announce Type: cross Abstract: Mobile graphical user interface (GUI) agents driven by vision-language models (VLMs) perceive the screen as rendered pixels and choose actions from wh
Starburst Data Inc. today is expanding its push into enterprise artificial intelligence with the introduction of a platform aimed at allowing organizations to run AI workloads directly on distributed
arXiv:2510.08555v2 Announce Type: replace Abstract: Existing controllable video generation methods are typically designed for rigid, task-specific settings, such as first-frame image-to-video, inpaint
arXiv:2511.11896v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have recently shown strong potential in vulnerability detection (VD). However, accurately detecting vulnerabiliti
arXiv:2605.28087v1 Announce Type: new Abstract: Service robots must infer object ownership to correctly interpret instructions such as 'bring me my cup.' However, ownership is a latent attribute that
arXiv:2605.26662v1 Announce Type: cross Abstract: This paper examines how estimates of AI use in scientific writing can be biased when evaluation methods ignore contextual differences across countries
arXiv:2605.26645v1 Announce Type: new Abstract: LLM-based knowledge-graph question answering (KGQA) delegates graph traversal to language models, turning each question into a sequence of local relatio
arXiv:2605.26827v1 Announce Type: cross Abstract: Recent benchmarks reveal that despite strong reasoning capabilities, large language models (LLMs) still struggle to faithfully apply complex contextua
arXiv:2605.26444v1 Announce Type: new Abstract: Large language models typically employ vocabularies of over 100k tokens, which creates a major computational bottleneck at the final linear projection l
arXiv:2605.23941v1 Announce Type: new Abstract: Alzheimer's disease is a neurodegenerative disorder marked by progressive declines in memory and language that reduce independence in daily life, motiva
arXiv:2605.25085v1 Announce Type: cross Abstract: We study the rate-distortion limits of online KV cache compression in autoregressive language models, formulating it as sequential Wyner-Ziv source co
arXiv:2605.23118v1 Announce Type: cross Abstract: Tracking tumor lesions across serial CT scans is essential for oncological response assessment. Existing automated methods face a fundamental trade-of
arXiv:2605.22937v1 Announce Type: new Abstract: Inference-time scaling can reduce errors in structured query generation, but methods to allocate the compute for query code generation remains underexpl
arXiv:2605.23597v1 Announce Type: new Abstract: Matching person names across heterogeneous records is a core challenge in entity resolution, especially within linguistically and culturally complex env
In this post, you will learn how to implement Recursive Language Models (RLM) using Amazon Bedrock AgentCore Code Interpreter and the Strands Agents SDK. By the end, you will know how to process docum
Agentmw is an open-source middleware framework designed to enhance AI agent reliability and efficiency across different models and frameworks. It addresses key operational challenges including mid-run
You can build a measurably better agent from data you already have, without retraining a thing. The data is what your experienced humans do when they correct the AI. Capture... The post Building a sel