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

Large Language Models as Data Preprocessors taaft Large Language Models (LLMs), typified by OpenAI's GPT, have marked a significant advancement in ar… 2023-08-30 published
Large Language Models for HVAC Operations in Building Energy Systems: A Critical Review of Methods, Applications, and Deployment Readiness taaft Building automation systems generate rich sensor data yet remain insight-poor because heterogeneous… 2026-09-04 published
Large language models generate functional protein sequences across diverse families Salesforce Traditional protein design is slow; applying LLM architectures to 280M sequences with control tags… Salesforce
Large Language Models in Resolving Contextual Knowledge Conflicts taaft Most prior works focused on conflicts between an LLM's internal parametric knowledge and externally… 2026-09-02 published
Large Language Models with At Most One Spike per Neuron taaft Leveraging their inherent sparse event-driven computation, spiking neural networks (SNNs) offer a p… 2026-09-04 published
Last Step Matters: Early Uncertainty Cannot Predict Failure in Long-Horizon Agents taaft Early failure prediction is important for long-horizon agents, as it enables timely intervention an… 2026-08-30 published
Last Translation Benchmark taaft For scientific progress, we need benchmarks that test the limits of state-of-the-art models, and ev… 2026-09-03 published
LaST-SR: Laplace-Inspired Steady-Transient Complex-Frequency Decomposition for Single Image Super-Resolution taaft Single-image super-resolution (SISR) requires global context modeling for structurally consistent r… 2026-09-02 published
Late Transformer Layers Recode Syntax Canonically: Evidence from Greek Scrambling and Cross-Layer Generalisation taaft Probing studies have established that syntactic information is decodable in early and middle transf… 2026-08-31 published
Latent Cluster Analysis for Vision-Language-Action Models taaft Vision-Language-Action (VLA) Models are increasingly used in robotics for their ability to ground l… 2026-09-02 published
Latent Energy Action Planning with World Models taaft Latent world models support efficient model predictive control from high-dimensional observations,… 2026-09-03 published
Latent Style-based Quantum Wasserstein GAN for Drug Design taaft The development of new drugs is a tedious, time-consuming, and expensive process, for which the ave… 2026-03-23 published
Latent unified smooth Hamiltonians for excited state chemistry taaft We describe a neural network architecture and training procedure designed to model electronic groun… 2026-09-01 published
Latent-Aligned Reasoning for Multimodal Recommendation taaft Multimodal Vision-Language Models (VLMs) have demonstrated remarkable capabilities in cross-modal u… 2026-09-04 published
LatentPress: Context Compression Beyond Text and Vision taaft Compressed context is usually carried as human-readable text or as rendered images that must be dec… 2026-09-01 published
Laya: A LeJEPA Approach to EEG via Latent Prediction over Reconstruction Tencent Electroencephalography (EEG) is a widely used tool for studying brain function, with applications i… 2026-03-17 published
LayerRecall: A State-Conditioned Memory Router for Long-Horizon Consistency in Video Generation taaft Autoregressive video diffusion enables scalable long-video generation by producing chunks from a bo… 2026-08-28 published
LCoT-GV: Graph Attention Networks for Verifying Long Reasoning Chains in Large Language Models taaft Large Reasoning Models produce Long Chains-of-Thought (LCoTs) which involve breaking down the probl… 2026-08-31 published
LDAC-Net: A Learnable Multi-Lag Differencing Attention-Convolution Network for Drift-Robust Recognition with Low-Cost MOX Gas Sensors taaft Portable electronic-nose systems based on low-cost metal-oxide (MOX) gas sensors offer a practical… 2026-08-26 published
Le MuMo JEPA: Multi-Modal Self-Supervised Representation Learning with Learnable Fusion Tokens taaft Self-supervised learning has emerged as a powerful paradigm for learning visual representations wit… 2026-03-25 published
LeakageBench: Document-Level Leakage Risk for Redacting Personally Identifiable Information in Document Images taaft Real-world personally identifiable information (PII) redaction often operates on document images---… 2026-09-02 published
LeanGRPO: Eliminating Redundant Recomputation in Diffusion RL taaft Diffusion reinforcement learning (RL) has recently achieved significant success in post-training im… 2026-09-03 published
LeanStream: A Speculate-and-Refine Streaming Framework for Efficient on-Device LLM Inference taaft On-device LLM inference is attractive for privacy and responsiveness, but remains challenging on mo… 2026-09-02 published
LeanVec: Searching vectors faster by making them fit taaft Modern deep learning models have the ability to generate high-dimensional vectors whose similarity… 2023-12-26 published
LeapTalk: Breaking the Latency-Quality Trade-off in Talking Head Generation taaft Long-form and real-time talking-head generation remains challenging due to a latency-quality trade-… 2026-07-29 published
Learn for Variation: Variationally Guided AAV Trajectory Learning in Differentiable Environments taaft Autonomous aerial vehicles (AAVs) enable data collection for sixth-generation Internet-of-Things ne… 2026-03-19 published
Learn from Whoever Is Right: Answer-Verified Multi-Teacher Distillation for Multi-Domain LLMs taaft Modern large language models (LLMs) rely on reinforcement learning to build strong capabilities in… 2026-09-02 published
Learnable composition for neural operators taaft Neural operators are fast, differentiable surrogates for physical simulation, but their accuracy of… 2026-09-02 published
Learnable Quantum Efficiency Filters for Urban Hyperspectral Segmentation taaft Hyperspectral sensing provides rich spectral information for scene understanding in urban driving,… 2026-03-27 published
Learning 3D Editing without Paired Supervision via Generative Prior Distillation taaft Instruction-guided 3D editing is essential for interactive content creation, yet it faces a signifi… 2026-09-04 published
Learning a Size-Weight Frontier for Synthetic-Augmented Inference taaft Synthetic data can improve statistical inference when real data are scarce, but naively treating sy… 2026-08-28 published
Learning Action Models with Conditional and Quantified Effects via Uncertainty-Guided Exploration taaft Accurate action models are critical for effective planning. Existing action-model learning methods… 2026-08-31 published
Learning by Distilling Context taaft Language models significantly benefit from context tokens, such as prompts or scratchpads. They per… 2022-09-30 published
Learning Continuous Regional Temperature Fields with Lead-Time and Resolution Queries taaft Accurate regional near-surface temperature forecasting is fundamental to short-range weather servic… 2026-08-26 published
Learning Cross-Joint Attention for Generalizable Video-Based Seizure Detection taaft Automated seizure detection from long-term clinical videos can substantially reduce manual review t… 2026-03-24 published
Learning Dynamics of Logits Debiasing for Long-Tailed Semi-Supervised Learning taaft Long-tailed distributions are prevalent in real-world semi-supervised learning (SSL), where pseudo-… 2026-08-31 published