Search: “context”

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:2609.17943v1 Announce Type: cross Abstract: Long-context LLM inference is bottlenecked by attention, whose repeated KV-cache reads make decoding memory-bound. Self-speculative decoding alleviate

arXiv:2609.19138v1 Announce Type: cross Abstract: Enabling robots to adapt to unfamiliar environments as readily as humans remains a moonshot goal of embodied AI. No finite collection of demonstration

arXiv:2609.16382v1 Announce Type: cross Abstract: A language model's representation geometry is not predetermined; it evolves as the model runs. A faithful account of that geometry must capture that d

arXiv:2501.03008v2 Announce Type: replace-cross Abstract: Context-aware machine translation can expose the evidence needed for pronoun choice, but standard fine-tuning does not explicitly prioritize t

arXiv:2607.17768v2 Announce Type: replace Abstract: Camouflage image generation (CIG) focuses on generating visually concealed objects that seamlessly blend into their backgrounds. Existing methods ty

arXiv:2606.21203v2 Announce Type: replace Abstract: Psycholinguistics studies show that human readers fall for coherence illusions: an incoherent discourse can seem coherent simply because a distracto

arXiv:2609.07663v1 Announce Type: cross Abstract: A wrong number is worse than no answer. Across factuality-critical domains -- audience metrics, scheduling and rights in media; dosages and lab values

arXiv:2609.07070v1 Announce Type: new Abstract: Spatio-temporal context has become increasingly crucial for visual tracking. However, most existing approaches extract spatio-temporal cues via discrete

arXiv:2609.04288v1 Announce Type: cross Abstract: Voice AI applications are gaining popularity as advances in large language models (LLMs) enable more natural and accessible spoken interactions. Servi

arXiv:2609.03384v1 Announce Type: new Abstract: In-Context Segmentation (ICS) aims to precisely segment arbitrary semantic concepts, such as objects or parts, given one or a few annotated visual exemp

arXiv:2609.03005v1 Announce Type: new Abstract: Many NLP tasks, such as summarization and extractive question answering, reduce to retrieving relevant content from documents under two constraints: cov

arXiv:2609.02336v1 Announce Type: new Abstract: Effective in-context learning (ICL) for complex reasoning relies on selecting the right demonstrations. Traditional retrieval methods based on surface s

arXiv:2609.00925v1 Announce Type: cross Abstract: Language models can ignore prompt evidence when it conflicts with memorized knowledge. Post-training can make models follow such evidence more reliabl

arXiv:2609.00097v1 Announce Type: cross Abstract: The development of long-context Large Language Models (LLMs) is constrained by the memory bandwidth bottleneck and quadratic complexity of the attenti

arXiv:2609.01043v1 Announce Type: cross Abstract: Uniform-state discrete diffusion models update all tokens in parallel while keeping every position revisable. Even when the commonly used top-p rule l

arXiv:2608.30270v1 Announce Type: new Abstract: Indirect speech acts (ISAs) require pragmatic reasoning over context, as directive intent can- not be inferred from surface form alone. Prior text-based

arXiv:2512.02337v2 Announce Type: replace Abstract: Growing demands from tasks like code generation, deep reasoning, and long-document understanding have made long-context generation a crucial capabil

arXiv:2608.28432v1 Announce Type: new Abstract: Recent advances in in-context learning (ICL) text-to-SQL have substantially improved execution accuracy on public benchmarks by assembling increasingly

arXiv:2608.28229v1 Announce Type: cross Abstract: Grammar-constrained decoding helps large language models produce syntactically valid structured outputs, such as code, JSON, and SQL. For context-free

arXiv:2509.19212v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) are increasingly deployed in real-world applications, yet their ability to make context-aware safety decisi

arXiv:2608.26103v1 Announce Type: cross Abstract: Zero-shot cross-task generalization, where a policy must execute manipulation tasks never seen during training, remains a central challenge in robot l

arXiv:2608.24119v1 Announce Type: cross Abstract: Visual demonstrations provide a natural interface for specifying image transformations that are difficult to describe exhaustively with text. However,

arXiv:2608.22745v1 Announce Type: cross Abstract: Emotion Recognition in Conversation (ERC) requires models to identify subtle emotional cues that are often distributed across distant dialogue turns.

arXiv:2608.22695v1 Announce Type: cross Abstract: Agent ecosystems now include thousands of MATS components (Models, Agents, Tools, and Skills), yet their discovery still relies on in-context routing.

arXiv:2608.20490v1 Announce Type: new Abstract: AI ethics frameworks treat values such as fairness, transparency, and accountability as universal and uniformly operationalizable across contexts. We ex

arXiv:2608.19181v1 Announce Type: cross Abstract: On-policy distillation (OPD) trains a student on its own responses using dense token-level guidance from a stronger teacher. In long-context tasks, ho

arXiv:2608.18084v1 Announce Type: new Abstract: Theorem proving in real-world Lean 4 projects is challenging because proofs often depend on project-specific context. While iterative refinement can use

arXiv:2510.07546v2 Announce Type: replace Abstract: We address the task of video style transfer with diffusion models, where the goal is to preserve the context of an input video while rendering it in

arXiv:2608.16745v1 Announce Type: new Abstract: Despite progress in instruction-based video editing, unimodal textual instructions inherently struggle to convey fine-grained textures and complex dynam

arXiv:2608.14277v1 Announce Type: cross Abstract: On-policy distillation (OPD) offers a promising way to transfer reasoning capabilities from stronger teacher models, but applying it to long-context r

arXiv:2608.13100v1 Announce Type: new Abstract: Contemporary online assessment systems rely primarily on browser lockdown, webcam monitoring, and behavioural analytics, yet remain vulnerable to attack

arXiv:2608.02830v1 Announce Type: cross Abstract: Many-shot in-context learning (ICL) lets vision-language models (VLMs) adapt from image--label demonstrations without weight updates, and is widely as

arXiv:2608.03048v1 Announce Type: cross Abstract: Long-context reasoning remains a critical bottleneck for large language models, as recent recurrent-memory approaches face two inherent challenges: se

arXiv:2608.03391v1 Announce Type: new Abstract: Precise anomaly localization over long-context time series is a crucial task in monitoring applications across clinical care, industrial operations, fin

arXiv:2508.12448v2 Announce Type: replace-cross Abstract: In-context learning (ICL) lets large language models (LLMs) solve new tasks from prompts alone, across an ever-widening range of domains, yet

arXiv:2608.02331v1 Announce Type: new Abstract: The same body posture can convey entirely different emotions depending on its surrounding context, yet most methods for recognising bodily emotions trea

arXiv:2607.27692v1 Announce Type: new Abstract: Top-K sparse attention reduces the cost of Softmax and value aggregation by attending to only a small subset of key--value (KV) entries. However, identi

arXiv:2512.07076v4 Announce Type: replace Abstract: Camouflage relies heavily on context, but current metrics used in camouflaged object segmentation ignore contextual cues. We identify two major draw

arXiv:2607.25532v1 Announce Type: new Abstract: Consider a model trained at a single hospital to predict patient recovery, where the measured feature X bundles the patient's true health signal (C) wit

arXiv:2607.24364v1 Announce Type: new Abstract: Predicting spatial gene expression from routine hematoxylin and eosin (H&E) images provides a practical complement to experimental spatial transcriptomi

arXiv:2607.24555v1 Announce Type: cross Abstract: Serving large language models at long context is bottlenecked by the key-value (KV) cache, which is read in full at every decode step. Attention keys

arXiv:2607.22729v1 Announce Type: cross Abstract: Backchannels, which signal listener states like empathy and understanding, are fundamental to natural human interaction. However, current approaches r

arXiv:2607.21927v1 Announce Type: new Abstract: Full self-attention in large language models scales as O(N^2), which limits long-context document analysis to 65,536 tokens and requires costly GPU clus

arXiv:2607.21503v1 Announce Type: new Abstract: Production AI agents' failures are less often due to an inability to reason well and more often because they cannot manage what is in their reasoning co

arXiv:2607.19077v1 Announce Type: new Abstract: Training video anomaly detectors is challenging due to the difficulty and cost of annotating diverse and rare abnormal events. Although recent large vis