Papers

3,241 in the directory.

Browse AI research papers and methods. Search paper profiles, read recorded summaries and follow source links for the full research.

A–Z Recently synced

KItCAT: Knowledge Injection via Input Corruption for Auto-regressive Training taaft LLMs acquire vast amounts of knowledge during pre-training, but often lack the specialized knowledg… 2026-08-31 published
kMaX-DeepLab: k-means Mask Transformer taaft The rise of transformers in vision tasks not only advances network backbone designs, but also start… 2022-07-08 published
Know Before Fix: QA-Driven Repository Knowledge Acquisition for Software Issue Resolution taaft LLM-based coding agents have significantly advanced automated software issue resolution, yet they r… 2026-07-13 published
Knowing Before Answering: Decoding Language Models for Reliable RAG taaft In Retrieval-Augmented Generation (RAG), retrieval may provide insufficient or conflicting informat… 2026-08-27 published
Knowing Is Not Enough: Information Retrievability as a Precondition to Effective LLM Oversight taaft Large language models (LLMs) are increasingly embedded in organizational work, yet their errors oft… 2026-09-02 published
Knowing When to Quit: A Principled Framework for Dynamic Abstention in LLM Reasoning taaft LLMs utilizing chain-of-thought reasoning often waste substantial compute by producing long, incorr… 2026-04-20 published
Knowledge Diffusion for Distillation Snap The representation gap between teacher and student is an emerging topic in knowledge distillation (… 2023-05-25 published
Knowledge Distillation Driven Semantic NOMA with GAN Refinement for 6G Robotic Vehicle Networks taaft To achieve sustainable intelligent mobility, 6G-empowered robotic vehicles (RVs) require high-fidel… 2026-08-27 published
Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall taaft Logit-based knowledge distillation (KD) is used to train smaller language models (LMs) via supervis… 2026-09-01 published
Knowledge-Guided Adversarial Training for Infrared Object Detection via Thermal Radiation Modeling taaft In complex environments, infrared object detection exhibits broad applicability and stability acros… 2026-03-26 published
Knowledge-Guided Failure Prediction: Detecting When Object Detectors Miss Safety-Critical Objects taaft Object detectors deployed in safety-critical environments can fail silently, e.g. missing pedestria… 2026-03-26 published
KnowVis: Knowledge-Centric Visual Summarization for Video Lectures taaft Video lectures are valuable educational resources, but their dense and lengthy formats often overwh… 2026-09-03 published
Koopman Operator Identification of Model Parameter Trajectories for Temporal Domain Generalization (KOMET) taaft Parametric models deployed in non-stationary environments degrade as the underlying data distributi… 2026-03-27 published
Koopman-Based Robust Model Predictive Control for Nonlinear Systems with Stochastic Intermittent Measurements taaft Intermittent state measurements pose fundamental challenges to model predictive control of constrai… 2026-09-02 published
KSG-Net: Key-Sparse and Global-Context Learning for Maritime 3D Ship Detection taaft Accurate 3D ship detection in maritime environments is critical for autonomous navigation, yet rema… 2026-09-02 published
KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks taaft Test-time scaling is a powerful approach to obtain better reasoning in large language models, but i… 2026-06-02 published
KVMem: Virtualizing Million-Token Agent Workspaces on a Consumer GPU taaft Modern LLM agents operate in persistent workspaces whose accumulated history can exceed both GPU KV… 2026-09-04 published
La Agente Óptima: Towards Agentic Self-Driving Laboratories taaft Self-driving laboratories (SDLs) combine automated experimentation with adaptive decision-making to… 2026-09-03 published
Label Semantic Expansion via Label Guided Neural Topic Modeling taaft Topic models are widely used for content analysis, where users often analyze corpora around predefi… 2026-08-31 published
Lagged Coupling: Internal Representations Become Readable Before They Become Causal taaft Across the full Pythia suite (160M-12B, eight checkpoints, four task families), a linear probe can… 2026-09-01 published
Landau theory of quenched criticality in linear in-context learning taaft In-context learning (ICL) allows a pretrained model to infer a new task from examples supplied in i… 2026-08-28 published
Landmark-Based Discrimination of Injury-Associated Athlete-Sessions from Minute-Resolution Multimodal Football Monitoring Data taaft Minute-resolution athlete monitoring is increasingly common, while injury annotation may exist only… 2026-09-03 published
Language is All a Graph Needs taaft The emergence of large-scale pre-trained language models has revolutionized various AI research dom… 2023-08-14 published
Language Is Not All You Need: Aligning Perception with Language Models Microsoft A big convergence of language, multimodal perception, action, and world modeling is a key step towa… 2023-02-27 published
Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spotting taaft Recently, Vision-Language Pre-training (VLP) techniques have greatly benefited various vision-langu… 2022-03-08 published
Language Models are Unsupervised Multitask Learners OpenAI Scaled GPT to 1.5B parameters and showed that "zero-shot" performance (performing tasks without any… OpenAI
Language Models Can Control Their Own Attention taaft Language models spend most of their attention on a small fraction of context, yet they read the ent… 2026-09-02 published
Language Proficiency Assessment from Eye Movements in Naturalistic Passage Reading taaft Standard language proficiency tests rely on linguistic tasks such as vocabulary, grammar and readin… 2026-08-31 published
Language-encoded network topology enables large language models to reason about complex networks taaft Networks describe systems in biology and beyond, from protein interactions and social relationships… 2026-09-03 published
Language-Guided Structure-Aware Network for Camouflaged Object Detection taaft Camouflaged Object Detection (COD) aims to segment objects that are highly integrated with the back… 2026-03-25 published
Language, Language Models, and What We're Talking About taaft Language models are commonly discussed as technical artefacts, but they are obviously shaped by the… 2026-09-03 published
Laplacian Frequency Hierarchies for Efficient 3D Gaussian Splatting Training taaft A key bottleneck in 3D Gaussian Splatting training is the continual growth of Gaussian primitives,… 2026-09-03 published
Large Language Model-Driven Context-Aware Eco-Feedback Generation and Evaluation taaft The objective of this study is to demonstrate the potential of generating context-aware eco-feedbac… 2026-09-02 published
Large Language Models (LLMs) for Telecom Root Cause Analysis (RCA): A Structured Reasoning Framework for Evidence-Grounded Diagnosis taaft Root cause analysis (RCA) is a critical task in telecom network operations, but diagnosing performa… 2026-09-02 published
Large Language Models Are Reasoning Teachers taaft Recent works have shown that chain-of-thought (CoT) prompting can elicit language models to solve c… 2022-12-20 published
Large Language Models as Annotators: Enhancing Generalization of NLP Models at Minimal Cost taaft State-of-the-art supervised NLP models achieve high accuracy but are also susceptible to failures o… 2023-06-27 published