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

SR-JEPA: Learning Predictive Latent State in 3D Scenes taaft Joint-embedding predictive architectures learn by predicting latent representations of missing obse… 2026-08-06 published
SR-Nav: Spatial Relationships Matter for Zero-shot Object Goal Navigation taaft Zero-shot object-goal navigation aims to find target objects in unseen environments using only egoc… 2026-03-19 published
SSAKG 2.0: An Open-Source Package for Structural Associative Sequence Memory and Context-Based Retrieval taaft This article presents SSAKG 2.0, an open-source software package for constructing and operating Str… 2026-09-01 published
SSMB: Self-Supervised Local Feature Detection under Motion Blur taaft Keypoint detection under motion blur remains a significant challenge, as blur distorts local image… 2026-08-27 published
Stability and Bifurcation Analysis of Nonlinear PDEs via Random Projection-based PINNs: A Krylov-Arnoldi Approach taaft We present a numerical framework for the stability and bifurcation analysis of nonlinear partial di… 2026-03-23 published
Stabilizing Camera-Controlled Novel View Synthesis at Inference Time taaft Training-free, camera-controlled novel view synthesis from a single image using pre-trained video d… 2026-09-03 published
Stable and Scalable Bundle Adjustment of Holistic 3D Structures taaft Bundle Adjustment (BA) is a cornerstone of 3D computer vision and has benefited from decades of adv… 2026-09-03 published
Stable Diffusion with Core ML on Apple Silicon Apple Engineering report + code enabling Stable Diffusion deployment via Core ML with optimizations for A… Apple
StainPresetNet: Stain Preset Network for Fast Multi-to-Multi Stain Normalization taaft Stain normalization reduces color variations caused by variations in staining protocols and imaging… 2026-09-01 published
STAIR (STructure Aware Information Retriever): A novel dataset and LLM based retriever for document structure augmentation taaft Retrieval Augmented Generation (RAG) is a key component for generating accurate and hallucination f… 2026-09-03 published
Stance Labels Fail When They Matter Most: The Projection Problem in Stance Detection taaft Stance detection is nearly always formulated as classifying text into Favor, Against, or Neutral. T… 2026-03-25 published
STARSS23: An Audio-Visual Dataset of Spatial Recordings of Real Scenes with Spatiotemporal Annotations of Sound Events taaft While direction of arrival (DOA) of sound events is generally estimated from multichannel audio dat… 2023-06-15 published
StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents taaft Computer-use agents are usually improved by strengthening perception: better models for reading a s… 2026-07-24 published
StateSwap: Probing Support-Elimination Hidden States in Multiple-Choice Questions taaft Large language models often answer the same multiple-choice question inconsistently when it is pose… 2026-09-01 published
Stay Within Your Bounds: Distance-Guided Decoding for Guaranteed Context-Free Grammar Compliance taaft Grammar-constrained decoding helps large language models produce syntactically valid structured out… 2026-08-28 published
Steered LLM Activations are Non-Surjective taaft Activation steering is a popular white-box control technique that modifies model activations to eli… 2026-04-10 published
SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF NVIDIA Model alignment with human preferences is an essential step in making Large Language Models (LLMs)… 2023-10-09 published
STENet: Superpixel Token Enhancing Network for RGB-D Salient Object Detection taaft Transformer-based methods for RGB-D Salient Object Detection (SOD) have gained significant interest… 2026-03-23 published
Stereo 4D Radar for 3D Object Detection: Integrating Geometric Alignment and Absolute Velocity Estimation taaft Four-dimensional (4D) Radar is a powerful sensing modality capable of detecting surrounding three-d… 2026-09-02 published
Stochastic Primal-Dual Decoding for Multiobjective Generative Recommender Systems Spotify Spotify's generative recommendation models are good at ranking individual items by relevance, but r… Spotify
Strategic Data Ordering: Enhancing Large Language Model Performance through Curriculum Learning taaft The rapid advancement of Large Language Models (LLMs) has improved text understanding and generatio… 2024-05-13 published
Stratified Consistency Distillation for Natural Language Formalization taaft Neurosymbolic reasoning has shown promising success in addressing complex reasoning tasks by combin… 2026-08-31 published
Stream3D: Sequential Multi-View 3D Generation via Evidential Memory taaft View-conditioned 3D generators such as SAM 3D, TRELLIS, and Hunyuan3D produce high-quality object r… 2026-05-20 published
StreamEMS: Streaming Video Understanding with Self-Evolving Memory Scheme for Vision-Language Models taaft Recently, many streaming video understanding methods have been proposed by constructing an external… 2026-08-28 published
Streaming4D: Accelerate 4D World Models via Block-wise Video Generation and Incremental Reconstruction taaft Current 4D generation paradigms are often bottlenecked by a sequential decoupling design: video is… 2026-09-01 published
StreamScout: Learning When to Look Deeper for Streaming Video Understanding taaft Streaming video understanding requires answering questions that arrive at arbitrary moments over an… 2026-08-31 published
Strengthening Recursive Constructions for Zero-Error Shannon Capacity taaft The exact Shannon capacity is unknown for every odd cycle beyond the five-cycle $C_5$, making odd c… 2026-08-31 published
Stress-Testing Efficient Responsible-AI Evaluation: When Compute Savings Change Benchmark Conclusions taaft Efficient evaluation changes the protocol used to support claims about model behavior, yet it is ra… 2026-08-31 published
Stringological sequence prediction I: efficient algorithms for predicting highly repetitive sequences taaft We propose novel algorithms for sequence prediction based on ideas from stringology. These algorith… 2026-03-27 published
Strong Drafts Need Compact Memories: Long-Context Speculative Decoding with Compressed KV Cache taaft Long-context LLM applications such as document summarization and multi-turn agents require generati… 2026-08-31 published
StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding Alibaba Recently, the pre-trained language model, BERT (and its robustly optimized version RoBERTa), has at… 2019-08-13 published
StructGPT: A General Framework for Large Language Model to Reason over Structured Data taaft In this paper, we study how to improve the zero-shot reasoning ability of large language models~(LL… 2023-05-16 published
Structural Hierarchy and Geometry in Molecular Representation Learning taaft Molecular self-supervised learning uses chemical structures to guide which molecular embeddings sho… 2026-08-30 published
Structure and Content-Guided Video Synthesis with Diffusion Models taaft Text-guided generative diffusion models unlock powerful image creation and editing tools. While the… 2023-02-06 published
Structure and Implementation of New Practical English Textbooks Driven by Artificial Intelligence taaft Artificial intelligence is changing the form of applied English materials from fixed paper sequence… 2026-09-02 published
Structure Aware Neural Architecture Search for Mixture of Experts taaft Neural Architecture Search (NAS) has so far rarely been applied to Mixture-of-Experts (MoE) models,… 2026-08-30 published