Knowledge catalogue
arXiv:2604.10200v1 Announce Type: new Abstract: As Vision-Language Models (VLMs) become integral to educational decision-making, ensuring their fairness is paramount. However, current text-centric eva
arXiv:2506.14493v3 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have shown great promise but require substantial computational resources during inference. Attackers can ex
arXiv:2508.03793v2 Announce Type: replace Abstract: Long-context large language models (LLMs), such as Gemini-2.5-Pro and Claude-Sonnet-4, are increasingly used to empower advanced AI systems, includi
arXiv:2509.23322v2 Announce Type: replace Abstract: With the continuous expansion of Large Language Models (LLMs) and advances in reinforcement learning, LLMs have demonstrated exceptional reasoning c
arXiv:2604.06765v1 Announce Type: cross Abstract: Recently, multi-Large Language Model (LLM) frameworks have been proposed to solve contextualized tasks. However, these frameworks do not explicitly em
arXiv:2609.40265v1 Announce Type: new Abstract: Real-world time-series applications increasingly require models that can handle time series forecasting, context-conditioned prediction, and language-ba
arXiv:2609.38332v1 Announce Type: cross Abstract: Test-time scaling improves model performance by allocating additional compute during inference. Using this compute effectively across multiple context
arXiv:2609.38260v1 Announce Type: cross Abstract: Values such as honesty, autonomy, and confidentiality are often regarded as general principles underpinning AI alignment. However, what it means to ac
arXiv:2609.20844v1 Announce Type: new Abstract: Deepresearch (DR) agents interact with real-world web environments through multi-turn search and visit, causing their contexts to grow rapidly over time
arXiv:2606.25170v1 Announce Type: cross Abstract: We study PAC learning in tabular discounted Markov decision processes with exogenous i.i.d. contexts, with discount factor gamma, finite state space m
arXiv:2604.23069v1 Announce Type: new Abstract: Large language model (LLM) agents often struggle in long-context interactions. As the agent accumulates more interaction history, context management app
arXiv:2602.00417v2 Announce Type: replace-cross Abstract: We present the first algorithms for generalized linear contextual bandits under shuffle differential privacy and joint differential privacy. W
arXiv:2603.17356v3 Announce Type: replace Abstract: Drug recommendation requires a deep understanding of individual patient context, especially for complex conditions like Parkinson's disease. While L
arXiv:2608.31038v1 Announce Type: new Abstract: Incremental Named Entity Recognition (INER) stands as a pivotal task in information extraction, emphasizing the successive identification of new entity
arXiv:2605.24803v1 Announce Type: new Abstract: A key goal in stochastic contextual linear bandits is to efficiently learn a near-optimal policy. Prior algorithms for this problem learn a policy by st
arXiv:2605.16747v1 Announce Type: new Abstract: We develop a quantitative statistical theory of transformers in the large-context regime by adopting the abstraction of contextual flow maps (CFMs): dyn
arXiv:2601.19300v2 Announce Type: replace Abstract: We introduce contextual queueing bandits, a new context-aware framework for scheduling while simultaneously learning unknown service rates. Individu
arXiv:2604.17091v1 Announce Type: new Abstract: Long-horizon large language model (LLM) agents are fundamentally limited by context. As interactions become longer, tool descriptions, retrieved memorie
arXiv:2604.16615v1 Announce Type: new Abstract: We introduce CoCo-LoRA, a multimodal, uncertainty-aware parameter-efficient fine-tuning method for text prediction tasks accompanied by audio context. E
We built a new way to train contextual embedding models, which encode each chunk of a document with the whole document in view. pplx-embed-v2-context-9b-preview sets a new state of the art on ConTEB a
arXiv:2510.07424v3 Announce Type: replace Abstract: We study linear contextual bandits with paid observations, where at each round the learner observes a context, selects an action, and may pay a fixe
arXiv:2608.28375v1 Announce Type: cross Abstract: Global goodness-of-fit and discrepancy statistics can establish that a sample departs from a reference distribution without identifying which observat
arXiv:2608.07593v1 Announce Type: cross Abstract: Context-aware recommender systems have long recognized that factors such as location, time, and weather shape where and what people choose to eat. Exi
arXiv:2606.10716v1 Announce Type: cross Abstract: Pre-trained language models (PLMs) have achieved strong performance in keyphrase extraction (KPE), largely due to their ability to generate rich conte
arXiv:2606.06428v1 Announce Type: new Abstract: Prior work has shown that large language models (LLMs) can translate unseen or low-resource languages by undergoing continued training or even by encodi
arXiv:2606.06022v1 Announce Type: new Abstract: Stance detection on social media is challenging due to short, noisy, and context-dependent language. While large language models (LLMs) show zero-shot g
arXiv:2606.05404v1 Announce Type: cross Abstract: Time series are often embedded in rich contexts that are essential for holistic modeling. Moreover, real-world practitioners often require end-to-end
arXiv:2605.28290v1 Announce Type: new Abstract: We study bandit learning in matching markets, where players and arms constitute the two market sides, and the players' utilities are linear in the arm c
arXiv:2610.09326v1 Announce Type: new Abstract: Video interactive storytelling enables viewers to actively steer how a video unfolds. However, once we allow viewers to intervene during generation, a n
arXiv:2601.17645v2 Announce Type: replace-cross Abstract: Internet audio-visual clips convey meaning through time-varying sound and motion, which extend beyond what text alone can represent. To examin
arXiv:2610.06056v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) frequently suffer from object hallucination. Existing training-free interventions primarily manipulate attention we
arXiv:2609.17488v1 Announce Type: new Abstract: We introduce LimiX-2, a new model in the LimiX family, developed through model and data scaling guided by our previously established scaling laws. LimiX
arXiv:2609.05333v1 Announce Type: new Abstract: A transformer language model assigns a single, context-independent vector to a word type at its embedding layer, yet is widely believed to individuate t
arXiv:2609.03148v1 Announce Type: new Abstract: Most prior works focused on conflicts between an LLM's internal parametric knowledge and externally provided context. In contrast, we investigate how LL
arXiv:2601.10034v3 Announce Type: replace-cross Abstract: Decision making often exhibits context dependence that is difficult to accommodate within a single non-invasive classical probability model. T
arXiv:2503.10647v2 Announce Type: replace Abstract: This study evaluated the diagnostic reliability of two Large Language Models (LLMs), Google Gemini 2.0 Flash and OpenAI ChatGPT-4o, across three dim
arXiv:2607.01916v1 Announce Type: new Abstract: Large language model agents can repair real repository issues, but they often spend large context budgets on whole-file reads, broad searches, and long
arXiv:2604.08149v2 Announce Type: replace Abstract: We consider a linear contextual bandit model where contexts and rewards are governed by a finite hidden Markov chain. We first revisit the simplifie
arXiv:2605.15692v1 Announce Type: new Abstract: We study episodic reinforcement learning with fixed reward and transition functions, but with episode-dependent admissible action sets that are observed
arXiv:2604.21308v1 Announce Type: cross Abstract: Enterprise LLM agents can dramatically improve workplace productivity, but their core capability, retrieving and using internal context to act on a us
arXiv:2509.25844v3 Announce Type: replace Abstract: When people query Vision-Language Models (VLMs) but cannot see the accompanying visual context (e.g. for blind and low-vision users), augmenting VLM
arXiv:2604.13275v1 Announce Type: new Abstract: Larger language models become simultaneously better and worse at handling contextual information -- better at ignoring false claims, worse at ignoring i
Claude Code's session management capabilities and 1 million token context window are highlighted in this post, which references an official Anthropic blog entry. The feature allows developers to maint
Claude Code's session management features and 1 million token context window capabilities are now documented on the official Claude Blog. The post, shared by Thariq on X, covers how developers can lev
arXiv:2610.21633v1 Announce Type: new Abstract: Finetuning a language model on narrowly misaligned data can make it broadly misaligned. Interleaving generic safety data is the most effective known in-
arXiv:2610.21518v1 Announce Type: new Abstract: Understanding how the human brain constructs meaning from real-world language remains a fundamental challenge, as semantics depend on context that varie
arXiv:2610.00910v1 Announce Type: cross Abstract: Human reasoning depends on how objects are related within propositions. extit{How do relations organize the language representations of contextual con
arXiv:2609.24955v1 Announce Type: cross Abstract: Visual instructions for physical tasks are typically authored in one context and followed in another, requiring users to translate demonstrated tools,
arXiv:2601.15397v3 Announce Type: replace-cross Abstract: The rapid emergence of new entities -- driven by cultural shifts, evolving trends, and personalized user data -- poses a significant challenge
arXiv:2609.00067v1 Announce Type: cross Abstract: External text can override conflicting image evidence in multimodal large language models, a failure we call multimodal contextual sycophancy. We intr
arXiv:2608.22679v1 Announce Type: new Abstract: Semantic segmentation has rapidly advanced with deep learning; however, challenges remain in effectively capturing local and global contexts as well as
arXiv:2608.17173v1 Announce Type: cross Abstract: Online decision making often requires navigating a landscape shaped by both dynamic contexts and strategic interactions. In competitive pricing, for e
arXiv:2606.09668v1 Announce Type: new Abstract: Contextual queueing bandits provide a framework for learning to schedule heterogeneous jobs under unknown context-dependent service rates. Under stochas
arXiv:2605.29645v1 Announce Type: cross Abstract: We study contextual bandits in the stochastic i.i.d. setting, where a learner observes contexts drawn from an unknown distribution, selects actions fr
arXiv:2605.18763v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly applied to analyzing wearable sensing data, which are long-term, multimodal, and highly personalized. A
arXiv:2605.03900v1 Announce Type: new Abstract: Frontier AI systems perform best in settings with clear, stable, and verifiable objectives, such as code generation, mathematical reasoning, games, and
arXiv:2604.27707v1 Announce Type: new Abstract: Current agentic memory systems (vector stores, retrieval-augmented generation, scratchpads, and context-window management) do not implement memory: they
arXiv:2604.18912v1 Announce Type: new Abstract: Discovering optimal designs through sequential data collection is essential in many real-world applications. While Bayesian Optimization (BO) has achiev
arXiv:2603.05744v2 Announce Type: replace Abstract: Current AI-powered code assistance tools often struggle with poorly-defined problem statements that lack sufficient task context and requirements sp
arXiv:2610.19804v1 Announce Type: new Abstract: We study finite stochastic partial monitoring (PM) games with side information, a paradigm of sequential learning with partial feedback. On each round t