Search: “context”

arXiv:2604.24693v1 Announce Type: new Abstract: Linear activation steering is a powerful approach for eliciting the capabilities of large language models and specializing their behavior using limited

arXiv:2512.10362v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) demonstrate impressive reasoning capabilities, but often fail to perceive fine-grained visual details

arXiv:2601.12078v2 Announce Type: replace Abstract: Large language models (LLMs) excel at general-purpose tasks, yet adapting their responses to individual users remains challenging. Retrieval augment

arXiv:2604.19639v1 Announce Type: cross Abstract: Modern world models are becoming too complex to admit explicit dynamical descriptions. We study safety-critical contextual control, where a Planner mu

Amplitude Inc. today introduced an embedded artificial intelligence support agent that helps users navigate digital products without leaving the application. Amplitude AI Assistant uses behavioral dat

arXiv:2601.15220v2 Announce Type: replace Abstract: We identify a novel phenomenon in language models: benign fine-tuning of frontier models can lead to privacy collapse. We find that diverse, subtle

arXiv:2604.07354v1 Announce Type: new Abstract: The accuracy frontier of speech-to-text systems has plateaued on academic benchmarks.1 In contrast, industrial benchmarks and adoption in high-stakes do

arXiv:2607.09015v2 Announce Type: replace Abstract: We study contextual bandit problems with correlated arms and access to surrogate reward signals produced by a machine learning model, motivated by a

arXiv:2601.22050v2 Announce Type: replace Abstract: In recent years, multilingual Large Language Models (LLMs) have become an inseparable part of daily life, making it crucial for them to master the r

arXiv:2602.03806v2 Announce Type: replace-cross Abstract: Training large language models (LLMs) for multi-turn code generation typically relies on online reinforcement learning (RL), in which models l

arXiv:2610.12467v1 Announce Type: cross Abstract: Text-conditioned motion generators produce trackable whole-body motion, but they have no notion of scene-dependent safety: the same action may target

arXiv:2610.06087v1 Announce Type: new Abstract: Game-theoretic attribution explains a model by assigning credit to its features or training examples. The least core has attracted interest as an altern

arXiv:2610.03202v1 Announce Type: cross Abstract: Flow Matching enables high-quality visual generation via continuous-time dynamics, but inference remains costly due to multiple sequential function ev

arXiv:2610.00840v1 Announce Type: cross Abstract: Transformer-based large language models (LLMs) such as RoBERTa represent text using contextual word embeddings (CWEs), which alter the embeddings asso

arXiv:2610.01980v1 Announce Type: new Abstract: Decision-focused learning for linear optimization is complicated by the discontinuity of the optimizer, where small cost errors may leave the decision u

arXiv:2606.20333v2 Announce Type: replace Abstract: Natural-language skills let agents reuse task knowledge, yet deploying a long Markdown document makes the model interpret that knowledge anew on eve

arXiv:2607.11684v2 Announce Type: replace-cross Abstract: Existing contextual multinomial logit (MNL) bandits model relevance-driven choice but ignore the potential benefits of within-assortment diver

arXiv:2609.34798v1 Announce Type: cross Abstract: Recent medical multimodal models have benefited from larger corpora, broader modality coverage, and stronger reasoning-oriented training, yet effectiv

arXiv:2609.33340v1 Announce Type: new Abstract: Contextual specialization can improve forecasting accuracy, but a correction selected on one historical interval may become unreliable under temporal di

arXiv:2606.14929v2 Announce Type: replace-cross Abstract: Modern recommendation systems increasingly rely on dynamically routing diverse queries to multiple embedding models. Despite its practical sig

arXiv:2602.04125v2 Announce Type: replace-cross Abstract: Modern digital platforms use contextual bandits to allocate valuable exposure and opportunities among competing participants. Fair treatment i

arXiv:2609.20179v1 Announce Type: new Abstract: Human perception, action and decision making unfold in sequences, but computational predictors are often domain-specific. This study computes and tests

arXiv:2609.14654v1 Announce Type: new Abstract: Convolutional neural networks (CNNs) are typically evaluated using held-out classification accuracy, an approach that presupposes predictions are based

arXiv:2609.13332v1 Announce Type: new Abstract: Automated landslide segmentation on Mars is one of the important tasks for understanding its surface processes, and all will aid in future space explora

arXiv:2609.12825v1 Announce Type: new Abstract: State Space Models (SSMs), particularly VMamba, have emerged as efficient alternatives for modeling long-range dependencies in medical image analysis. H

arXiv:2609.06880v1 Announce Type: new Abstract: Reasoning over language instructions in embodied tasks such as robotics often requires understanding spatial relations from a speaker's situated perspec

arXiv:2609.06083v1 Announce Type: new Abstract: To make optimal joint pricing and inventory control decisions is a critical challenge for modern retailers. In practice, retailers face changing market

arXiv:2609.00048v1 Announce Type: cross Abstract: GUI world models are increasingly evaluated as one-step next-screen predictors, yet their intended use is often as multi-step environments for GUI age

arXiv:2608.30065v1 Announce Type: cross Abstract: Large language models (LLMs) demonstrate strong Helpfulness, Harmlessness, and Honesty (3H) alignment in English-centric settings, but these gains tra

arXiv:2308.15618v3 Announce Type: replace Abstract: Squamous cell carcinoma (SCC) is one of the most common cancer subtype, with an increasing incidence and a significant impact on cancer-related mort

arXiv:2608.22028v1 Announce Type: new Abstract: This paper presents a conceptual design for a proactive human assisting robot system capable of recognizing human activities and responding proactively.

arXiv:2608.22014v1 Announce Type: new Abstract: Automated prompt and skill optimization typically produces a single static instruction that is reused across inference instances until the next optimiza

arXiv:2608.21928v1 Announce Type: new Abstract: In embodied AI, safety risk can be latent: a benign instruction and a safe scene become hazardous only when composed. Prior work has advanced embodied s

arXiv:2608.20402v1 Announce Type: cross Abstract: Biomedical knowledge graphs (KGs) are pivotal for knowledge organization, yet traditional binary relations often struggle to represent the conditional

arXiv:2603.19997v2 Announce Type: replace Abstract: We investigate the separation of literal interpretation from contextual inference in a collaborative block-building tasks, where an agent must resol

arXiv:2608.16269v1 Announce Type: new Abstract: Recent advances in neural topic models with pre-trained language models (PLMs) have achieved strong performance by leveraging general-domain pre-trainin

arXiv:2608.07642v1 Announce Type: new Abstract: Aligning large language models (LLMs) with human values remains a major challenge, especially for trustworthy AI. While existing approaches such as RLHF

arXiv:2608.03035v1 Announce Type: new Abstract: Prior work has shown that LLMs encode the truth of factual propositions along linear directions in activation space. It's unclear how these representati

arXiv:2608.03142v1 Announce Type: cross Abstract: We study contextual dynamic pricing with arbitrary covariate sequences and bounded, possibly nonbinary purchase quantities. Demand follows a semiparam

arXiv:2607.15856v2 Announce Type: replace Abstract: Naturalistic language comprehension requires listeners to process both local probabilistic expectations and contextual semantic relations. This stud

arXiv:2607.25184v1 Announce Type: new Abstract: Human language exhibits lawful structure at the level of words (frequency, vocabulary growth) and word pairs (co-occurrence across distance). Here we sh

arXiv:2607.13686v1 Announce Type: new Abstract: We study the contextual combinatorial semi-bandit (CCSB) problem with general reward function approximation. At each round, the learner observes a conte

arXiv:2607.08117v1 Announce Type: new Abstract: Contextual biasing seeks to integrate external knowledge into automatic speech recognition (ASR) systems to accurately recognize domain-specific entitie

arXiv:2506.08630v3 Announce Type: replace Abstract: A universal controller for any robot morphology would greatly improve computational and data efficiency. Steps have been made towards such multi-rob

arXiv:2607.05625v1 Announce Type: new Abstract: Wound monitoring is a critical yet underserved clinical challenge, where timely identification of severe adverse events (SAEs) such as infection, tissue

arXiv:2605.06142v2 Announce Type: replace-cross Abstract: When people recount personal memories, they often refer to people, places, and events indirectly, relying on con-textual cues rather than expl