Knowledge catalogue
arXiv:2605.08475v1 Announce Type: cross Abstract: Mechanistic accounts of in-context learning (ICL) have identified iterative algorithms for linear regression and related linear prediction tasks, ofte
arXiv:2605.07123v1 Announce Type: new Abstract: In-context reinforcement learning (ICRL) refers to the ability of RL agents to adapt to new tasks at inference time without parameter updates by conditi
arXiv:2605.07454v1 Announce Type: new Abstract: In-context learning enables large language models to adapt to new tasks, but their performance is highly sensitive to the selected examples. Finding eff
arXiv:2605.03644v1 Announce Type: new Abstract: Many-Shot In-Context Learning (ICL) has emerged as a promising paradigm, leveraging extensive examples to unlock the reasoning potential of Large Langua
arXiv:2511.07328v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) methods enhance LLM performance by efficiently filtering relevant context for LLMs, reducing hallucinations and
arXiv:2605.01752v1 Announce Type: new Abstract: We study linear dueling bandits in volatile environments characterized by the simultaneous presence of post-serving contexts, delayed feedback, and adve
arXiv:2602.03216v2 Announce Type: replace Abstract: The quadratic complexity of attention remains the central bottleneck in long-context inference for large language models. Prior acceleration methods
arXiv:2601.11908v2 Announce Type: replace Abstract: Large language models (LLMs) struggle with reasoning over long contexts where relevant information is sparsely distributed. Although plan-and-execut
arXiv:2604.26413v1 Announce Type: cross Abstract: This paper presents Quantum Gatekeeper, a context-bound image steganography framework where successful payload recovery depends on both cryptographic
arXiv:2604.25132v1 Announce Type: new Abstract: Instruction-tuning datasets often contain substantial redundancy and low-quality samples, necessitating effective data selection methods. We propose an
arXiv:2505.16518v3 Announce Type: replace-cross Abstract: Incorporating external knowledge is crucial for knowledge-intensive tasks, such as question answering and fact checking. However, language mod
arXiv:2604.23267v1 Announce Type: new Abstract: Large language models (LLMs) operate in two fundamental learning modes - fine-tuning (FT) and in-context learning (ICL) - raising key questions about wh
arXiv:2604.20348v1 Announce Type: cross Abstract: Language Models (LLMs) have emerged as powerful reasoning engines for embodied control. In particular, In-Context Learning (ICL) enables off-the-shelf
arXiv:2506.19977v2 Announce Type: replace Abstract: Understanding which parts of the retrieved context contribute to a large language model's generated answer is essential for building interpretable a
arXiv:2604.17574v1 Announce Type: new Abstract: Distractor generation (DG) remains a labor-intensive task that still significantly depends on domain experts. The task focuses on generating plausible y
arXiv:2604.18091v1 Announce Type: new Abstract: Recent multimodal large language models have shown promising ability in generating humorous captions for images, yet they still lack stable control over
A free, open-source CLI coding agent that runs locally using Ollama and can read, write, and edit files while running shell commands through natural language. The tool supports Claude API as an altern
arXiv:2510.04008v5 Announce Type: replace Abstract: Softmax Attention has a quadratic time complexity in sequence length, which becomes prohibitive to run at long contexts, even with highly optimized
arXiv:2604.16542v1 Announce Type: cross Abstract: Safety guardrails have become an active area of research in AI safety, aimed at ensuring the appropriate behavior of large language models (LLMs). How
arXiv:2503.14281v4 Announce Type: replace-cross Abstract: AI coding assistants are widely used for tasks like code generation. These tools now require large and complex contexts, automatically sourced
arXiv:2604.15547v1 Announce Type: cross Abstract: The fundamental challenge of using Large Language Models (LLMs) for reliable, enterprise-grade analytics, such as sentiment prediction, is the conflic
arXiv:2602.20091v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) enhances large language models (LLMs) by conditioning generation on retrieved external documents, but the effec
arXiv:2604.14922v1 Announce Type: cross Abstract: Reinforcement Learning (RL) has emerged as a critical driver for enhancing the reasoning capabilities of Large Language Models (LLMs). While recent ad
arXiv:2604.13849v1 Announce Type: cross Abstract: The rapid proliferation of Model Context Protocol (MCP)-based agentic systems has introduced a new category of security threats that existing framewor
arXiv:2604.13883v1 Announce Type: new Abstract: Modern machine learning models typically represent inputs as fixed points in a high-dimensional embedding space. While this approach has been proven pow
We’ve also added support for 90+ plugins in Codex, giving it more ways to gather context and take action across the tools you already use for docs, project management, code review, creative work, depl
This post discusses how handling large context windows (around one million tokens) in AI systems requires more sophisticated session management strategies rather than simplified approaches, contrary t
arXiv:2604.06784v2 Announce Type: replace Abstract: Previous research on multi-party dialogue generation has predominantly leveraged structural information inherent in dialogues to directly inform the
arXiv:2601.10775v2 Announce Type: replace Abstract: We propose a novel LLM-based framework for reasoning in discrete, game-theoretic tasks, illustrated with Tic-Tac-Toe. The method integrates in-conte
arXiv:2602.18679v2 Announce Type: replace Abstract: Large-scale foundation models for scientific machine learning adapt to physical settings unseen during training, such as zero-shot transfer between
arXiv:2603.27817v3 Announce Type: replace-cross Abstract: Street-level imagery contains personally identifiable information (PII), some of which is context-dependent. Existing anonymization methods ei
memory is just context -> the harness decides what gets remembered, how, and when memory ownership = agent ownership deepagents lets you own your memory: agent-scoped, user-scoped, or org-level, all i
Harrison Chase, associated with LangChain, shared or was cited in a post on X criticizing OpenAI's server-side memory compaction and Anthropic's handling of context as problematic precedents for AI me
@hwchase17 @sarahwooders like a the old children's school flipbook - each one wakes up, takes in the context(memory) via harness does its thing, then rests.... next flip book page, the harness manages
arXiv:2610.18848v1 Announce Type: new Abstract: In-context robot learning enables robots to acquire new behaviors from demonstrations without test-time parameter updates. However, visual and kinematic
arXiv:2610.18741v1 Announce Type: new Abstract: Reliable detection of pedestrians and road users is essential for the safe operation of autonomous vehicles. However, this task becomes increasingly cha
arXiv:2610.16694v1 Announce Type: new Abstract: Adversarial detection on evolving attributed graphs faces two challenges: fraud labels arrive late or not at all, and natural distributional drift erode
arXiv:2601.13155v3 Announce Type: replace-cross Abstract: Long-context inference enhances the reasoning capability of Large Language Models (LLMs), but incurs significant computational overhead. Token
arXiv:2610.14861v1 Announce Type: new Abstract: Time-series forecasting plays a vital role in a wide range of real-world applications. Recent approaches have achieved strong performance by modeling te
arXiv:2610.13411v1 Announce Type: cross Abstract: Traditional system identification typically involves two steps: initially, training data is processed to estimate a model of the system of interest; t
arXiv:2607.17710v2 Announce Type: replace Abstract: Large Language Models (LLMs) have had a remarkable impact across many areas of machine learning. However, recent studies have shown that they strugg
arXiv:2610.11287v1 Announce Type: cross Abstract: Long-horizon agents compact their history to continue within a finite context window, but a textual summary alone may not support every subsequent dec
arXiv:2610.10761v1 Announce Type: cross Abstract: Linear attention is a tractable model for understanding the mechanisms governing in-context learning in transformers. For linear regression tasks, rec
arXiv:2610.09375v1 Announce Type: new Abstract: Organizations increasingly use frontier language models to analyze customer feedback, but answer quality also depends on how that feedback is organized
arXiv:2610.08816v1 Announce Type: new Abstract: Long-range temporal dependence poses a resource question for sequence models: for a specified predictive-memory law, how much state, context, or dynamic
arXiv:2605.06537v2 Announce Type: replace Abstract: Medical multimodal large language models (MLLMs) have advanced image understanding and short-video analysis, but real clinical review often requires
We released Aplomb 1 today, a 5.3B decision model with open weights. It reads up to 1M tokens of text, JSON, images, video and audio in a single request, and on our API it makes a decision on a 1M-tok
In CUDA 13.1 “green contexts” let applications explicitly partition a GPU’s execution resources—such as Streaming Multiprocessors (SMs) and work‑queue slots—within one process. By assigning dedicated
arXiv:2610.05333v1 Announce Type: new Abstract: Generative foundation models are attracting interest for their ability to produce desired outputs from demonstrations given at inference time, without u
arXiv:2610.06006v1 Announce Type: new Abstract: We study contextual queueing bandits, where a learner schedules jobs while learning unknown service rates modeled by logistic functions of job-server fe
arXiv:2610.02494v1 Announce Type: new Abstract: Automatic horizon tracking is a foundational task in 3D seismic interpretation. Most existing deep learning approaches formulate it as dense semantic se
arXiv:2610.00418v1 Announce Type: new Abstract: Scaling Transformers to long contexts is constrained by the quadratic cost of self-attention and the linear growth of key-value cache memory transfer. S
arXiv:2610.00544v1 Announce Type: new Abstract: Streaming world models should render a place consistently across repeated visits. Directly supervising such revisits requires training samples that capt
New paper from Microsoft on compressing agent context at test time. If your agent gets worse as its interaction history grows, this method is worth a look. FOCUS asks which past interactions the agent
arXiv:2609.38908v1 Announce Type: cross Abstract: Single-cell transcriptomics enables profiling of cellular states at unprecedented resolution, but its high dimensionality, sparsity, and technical bat
arXiv:2609.38560v1 Announce Type: new Abstract: Mycosis fungoides (MF) is a rare form of cutaneous T-cell lymphoma that is often misdiagnosed in early stages due to its visual similarity to benign inf
arXiv:2609.39920v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) exhibit strong multimodal in-context learning (ICL) capabilities, yet this ability degrades substantially as mode
arXiv:2609.39143v1 Announce Type: new Abstract: Long-horizon agent interactions generate useful but noisy experience, and retraining models to absorb it is expensive. Context-evolving agents therefore
arXiv:2609.36526v1 Announce Type: cross Abstract: Long-horizon agents require context compression to manage growing interaction histories. Compression quality, however, is ultimately determined by dow
arXiv:2609.37590v1 Announce Type: new Abstract: LLM agents accumulate interaction histories that grow linearly with task length, causing quadratic inference cost scaling and performance degradation fr