Knowledge catalogue
arXiv:2609.36265v1 Announce Type: cross Abstract: Large language models can learn abstract rules from just a few in-context examples, but how their internal mechanisms activate as examples accumulate
arXiv:2609.37684v1 Announce Type: new Abstract: Adaptive Cruise Control (ACC) systems are typically calibrated for an average driver, often resulting in a mismatch between vehicle behavior and individ
arXiv:2609.36384v1 Announce Type: new Abstract: Relational in-context learning (ICL) conditions predictions on the labeled support examples and their linked tables, creating a failure mode when the su
arXiv:2609.36529v1 Announce Type: cross Abstract: Recurrent neural networks (RNNs) compress the historical context into a memory state of fixed size, thus allowing for constant-time inference. The mem
arXiv:2609.32395v1 Announce Type: cross Abstract: The KV cache of a transformer entangles every token's representation with its entire prefix: a passage encoded once cannot be reused under a different
arXiv:2606.16694v2 Announce Type: replace Abstract: Transformers perform computations through many successive attention and feedforward blocks, allowing them to learn complex correlations between a la
arXiv:2609.33609v1 Announce Type: new Abstract: In-context learning (ICL) is crucial for boosting the inference performance of large language models (LLMs). However, the effectiveness of ICL in LLMs i
arXiv:2609.30471v1 Announce Type: cross Abstract: Reference-based LLM-as-a-judge evaluation assumes the reference answer is the target. In deployed agentic systems that operate over dynamic entities (
arXiv:2609.31434v1 Announce Type: new Abstract: Task-agnostic assistive exoskeleton control based on human intention offers greater flexibility than conventional approaches that rely on predefined tas
arXiv:2609.29995v1 Announce Type: cross Abstract: AI teaching assistants (AI TAs) backed by large language models (LLMs) and pedagogical guardrails are increasingly being integrated into programming c
arXiv:2609.29060v1 Announce Type: cross Abstract: Transformers achieve remarkable performance by jointly learning broad families of tasks during pretraining and adapting to unseen tasks from only a sh
arXiv:2609.27354v1 Announce Type: cross Abstract: Generative AI systems are increasingly deployed to address domain problems. These systems operate under technical, regulatory, institutional, and norm
arXiv:2609.27523v1 Announce Type: new Abstract: Breast image classification requires local detail and global tissue context, yet these cues can weaken as representations deepen. We present M3D-Net, a
Enterprise data startup Ekai Inc. today announced 1.7 million in new funding for software that builds the business context artificial intelligence agents need before they can be trusted with corporate
arXiv:2609.26422v1 Announce Type: new Abstract: Detecting emotions is necessary for building systems that can accurately and adaptively interact with humans. Speech Emotion Recognition (SER) has becom
arXiv:2609.25623v1 Announce Type: new Abstract: More privileged information does not always make a better teacher. We study this tension in on-policy self-distillation (OPSD), where a frozen copy of t
arXiv:2609.22114v1 Announce Type: new Abstract: Context compression is widely proposed as a way to cut the token bill of LLM coding agents, and public benchmarks report that aggressive compression pre
arXiv:2609.22697v1 Announce Type: new Abstract: Recently, text-to-speech systems have made significant progress in speech expressiveness and controllability. However, the speaking style of generated s
Recommended if you work on agent memory. Retrieval is the hardest memory problem in most harnesses because agents keep pulling stale context. AML tests this with a coding track of 150 software tasks,
arXiv:2609.24559v1 Announce Type: new Abstract: We present t_0, a family of open-weights foundation models for forecasting with multivariate context. We release its first two members: exttt{t0-alpha}
arXiv:2607.18840v2 Announce Type: replace Abstract: World Action Models (WAMs) offer a promising paradigm for robotic manipulation by jointly modeling visual state transitions and robot actions. Howev
arXiv:2609.21595v1 Announce Type: new Abstract: In-context learning using Large Language Models (LLMs) offers a compelling path to training-free post-OCR correction, yet its effectiveness for Devanaga
arXiv:2609.21241v1 Announce Type: new Abstract: Producing accurate annotations for deep learning based image segmentation is both costly and labor intensive. This challenge is especially evident in wi
arXiv:2609.20971v1 Announce Type: new Abstract: Long-context large language model inference is increasingly limited by prefill, where dense self-attention processes the entire prompt before generation
arXiv:2609.16592v1 Announce Type: new Abstract: This paper presents an end-to-end approach for generating context-specific large language model (LLM) benchmark datasets by combining expert input with
arXiv:2505.24846v3 Announce Type: replace Abstract: Reward modeling is a key step in building safe foundation models when applying reinforcement learning from human feedback (RLHF) to align Large Lang
arXiv:2609.12839v2 Announce Type: replace-cross Abstract: The proliferation of highly capable open-weight Small Language Models (SLMs) democratizes access to advanced cybersecurity capabilities, posin
arXiv:2609.10177v1 Announce Type: new Abstract: In-context learning (ICL) is widely used in multimodal large language models (MLLMs) and achieves strong performance across a wide range of multimodal t
arXiv:2609.10132v1 Announce Type: cross Abstract: The development of generative artificial intelligence resources enables opportunities of speeding up systems and engineering design work. This contrib
arXiv:2609.11872v1 Announce Type: cross Abstract: Continuous glucose monitoring (CGM) provides high-frequency measurements of glucose dynamics and enables short-term glucose forecasting for diabetes m
Reuters: DeepSeek debuts DeepSeek-V4.1-Flash, its smallest model built on its new Causal Encoder-Decoder architecture, with 552B backbone parameters and 1M-token context — Chinese artificial intellige
This is a brilliant paper. It's of the cleanest long-context agent designs I have seen in the past couple of months. Sequential memory agents read chunks one after another while maintaining a compact
Try this prompt in Claude chat to give it more context about yourself: Interview me in depth using free text, or askuserquestion tool when multiple choice works, about relevant parts of my life you do
Israeli artificial intelligence startup Euno says it’s trying to build an AI-native “context brain” for autonomous agents after raising 23 million in an early-stage funding today. The Series A round w
arXiv:2609.06356v1 Announce Type: new Abstract: U-Net remains a practical baseline for image segmentation because of its simple encoder-decoder structure and skip connections. However, the bottleneck
Banger paper from Microsoft and Cornell. If you have looked at thinking tokens and decided you cannot afford the context, read this one. (bookmark it) A pause token buys the model extra compute for ea
arXiv:2609.02573v1 Announce Type: new Abstract: Current evaluations and training of multimodal models predominantly focus on multi-image tasks, largely overlooking interleaved text-image scenarios. In
arXiv:2609.01827v1 Announce Type: new Abstract: Structural magnetic resonance imaging (MRI) images are sometimes corrupted over a contiguous set of slices, where acquisition, motion, hardware, or reco
arXiv:2609.00865v1 Announce Type: cross Abstract: Production agent harnesses such as Claude Code and Qwen-Agent compress context during rollout, but training under compression creates a conditioning p
arXiv:2609.00618v1 Announce Type: cross Abstract: We investigate the role of conversational context modeling in user preference tracking for Conversational Recommendation Systems (CRSs). In this regar
arXiv:2608.30327v1 Announce Type: new Abstract: Fine-tuning can improve legal question-answering accuracy without improving how models use law supplied in context. We study this distinction in bilingu
arXiv:2603.23938v2 Announce Type: replace Abstract: Most testbeds for omni-modal models assess multimodal understanding via textual outputs, leaving it unclear whether these models can properly speak
As AI adoption accelerates and language models become commodities, enterprises are discovering that knowledge graphs provide the critical layer for turning scattered data into usable, real-time contex
arXiv:2608.27529v1 Announce Type: new Abstract: Streaming 3D reconstruction from extremely long videos requires estimating camera motion and scene geometry online under bounded memory and computation.
I was using UD-Q3_K_XL until now with more than 140000 context. Quality wise it's very good, very few erroneous tool calls. Then I saw many others here reporting good results with IQ3_XXS, so I gave i
AI storage infrastructure is becoming a more consequential planning issue as organizations move from model training toward agentic AI. As agents reason, act and reassess, they build longer contexts an
arXiv:2608.22963v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) are increasingly deployed as multi-step agents, where explicit reasoning supports task decomposition and tool c
arXiv:2606.16151v2 Announce Type: replace Abstract: Many reasoning tasks require models to reason over input context, from document-grounded question answering to rule-based deduction. Chain-of-Though
arXiv:2608.21410v1 Announce Type: new Abstract: Robots are increasingly entering everyday environments where privacy is shaped not only by data practices, but also by spatial, bodily, social, and rela
arXiv:2608.22354v1 Announce Type: cross Abstract: Delta-Rule recurrent models maintain a fixed-size state, enabling O(1) inference memory but potentially becoming unstable under extreme-context extrap
arXiv:2608.22023v1 Announce Type: new Abstract: Context-adaptive Kalman filters calibrate their noise covariance matrices Q and R from innovation residuals via online regression. When the underlying s
arXiv:2504.11055v3 Announce Type: replace Abstract: Zero-shot anomaly detection and localization aims to learn from source-domain data and generalize to unseen target domains without target-domain sam
NVIDIA Groq 3 LPX, when paired with the Vera Rubin NVL72 platform, delivers a record‑setting 3,431 output tokens/second on the Artificial Analysis 100K context benchmark using Gemma 4 31B, demonstrati
arXiv:2608.19875v1 Announce Type: cross Abstract: Patients often submit short, underspecified queries to healthcare chatbots that lack the patient-specific information needed to determine an appropria
arXiv:2608.19463v1 Announce Type: new Abstract: Anomaly detection in tabular data is challenging because abnormal samples often arise as violations of cross-feature dependencies rather than simple mar
arXiv:2608.18576v1 Announce Type: new Abstract: A convolutional sequence labeler's receptive field is routinely treated as the extent of the model's usable context: it sets dilation schedules, bounds
arXiv:2608.18979v1 Announce Type: new Abstract: Semantic segmentation demands a careful balance between accuracy, efficiency, and scalability, which remains difficult to achieve for high-resolution im
arXiv:2608.15962v1 Announce Type: new Abstract: Long-context reasoning remains computationally expensive for large language models due to the quadratic complexity of attention over text tokens. Visual
arXiv:2608.16370v1 Announce Type: new Abstract: Task completion is the standard metric for evaluating context compression, yet it is incomplete: compression can increase an agent's interaction cost by
arXiv:2608.14528v1 Announce Type: new Abstract: This study investigates the methodological and theoretical properties of session handover in applications that use large language models. A task may con