Blog Promote Sign in Sign up

Catalogs

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
Explore other catalogs
Models Datasets Demos Devices Robots MCPs Papers Investors Fundraises Repositories News
How to choose papers

Use the summary to find relevant work, then read the original paper. Compare the method, evaluation setting, baselines and limitations with your own problem. Check whether code and datasets are available; a reported benchmark result may not transfer to your use case.

Understand our sources and data limits

  1. SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-DomainText-to-SQL Task taaft Most existing studies in text-to-SQL tasks do not require generating complex SQL queries with multi… 2018-10-11 published
  2. Synth-JDoc: Synthesizing a Japanese Document Image Dataset for OCR with Diverse Layouts and Embedded Images taaft The ability of Large Vision Language Models (LVLMs) to read text within document images is crucial,… 2026-08-28 published
  3. Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models taaft We introduce Generalized Instruction Tuning (called GLAN), a general and scalable method for instru… 2024-02-20 published
  4. Synthetic Linguistic Agency: How an Embodied Mortal Agent Learns Linguistic Affordances through Consequential Social Experience taaft Contemporary language models can converse fluently and influence human decisions, yet their exchang… 2026-08-28 published
  5. Synthetic Mixed Training: Scaling Parametric Knowledge Acquisition Beyond RAG taaft Synthetic data augmentation helps language models learn new knowledge in data-constrained domains.… 2026-03-24 published
  6. Synthetic Rewriting as a Quality Multiplier: Evidence from Portuguese Continued Pretraining taaft Synthetic data generation through document rewriting has emerged as a promising technique for impro… 2026-03-25 published
  7. Synthetic Semantic Supervision for Contrastive Code Representation Learning in Small Transformers: An Empirical Study taaft General-purpose code embeddings power tools for code search, classification, and retrieval. Compact… 2026-09-03 published
  8. T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search taaft While prior red-teaming efforts have focused on eliciting harmful text outputs from large language… 2026-03-21 published
  9. T2LSC-Bench: Benchmarking Localized Semantic Control in Text-to-Image Generation taaft Recent text-to-image models have become increasingly capable of rendering explicit text, but reliab… 2026-09-02 published
  10. TableLlama: Towards Open Large Generalist Models for Tables taaft Semi-structured tables are ubiquitous. There has been a variety of tasks that aim to automatically… 2023-11-15 published
  11. TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy taaft Tables contain factual and quantitative data accompanied by various structures and contents that po… 2024-06-03 published
  12. TabScope: Question-Adaptive Scope Selection for Table Question Answering taaft Large Language Models (LLMs) have shown strong performance on table question answering, yet their a… 2026-09-03 published
  13. Tabular Deep Learning for Algorithmic Trading: Cross-Regime Bayesian Optimisation for Equity Signal Generation taaft Algorithmic trading now represents a market exceeding $20 billion, where even marginal gains in sig… 2026-08-27 published
  14. TacForcing: Streaming Action Generation with Execution-Time Tactile Feedback taaft Contact-rich manipulation requires adapting to contact states that can evolve substantially within… 2026-08-26 published
  15. TACS: Trajectory-Aware Candidate Selection for LLM Jailbreak Suffix Optimization taaft Gradient-based jailbreak suffix optimization methods typically update the suffix by retaining the c… 2026-08-30 published
  16. TADP: Task-Aware Deformable Prediction for Single-Stage 3D Object Detection taaft Most single-stage 3D object detectors complete different tasks with the same extracted features. Ne… 2026-08-27 published
  17. TAG: Target-Agnostic Guidance for Stable Object-Centric Inference in Vision-Language-Action Models taaft Vision--Language--Action (VLA) policies have shown strong progress in mapping language instructions… 2026-03-25 published
  18. Tail-Likelihood Reinforcement Learning taaft Reinforcement learning typically optimizes average reward. For generative policies, the average can… 2026-09-02 published
  19. Tail-Replay: Escaping the Curse of Linear Attention in Prefix Caching for Hybrid LLMs taaft Hybrid large language models interleave full-attention layers with linear-attention layers to reduc… 2026-08-31 published
  20. TailorCoPilot: Enabling Agentic Pattern Making with Version-Controlled State Tracking taaft Experience-driven manufacturing, such as garment pattern making, faces a severe generational skills… 2026-08-26 published
  21. TAKE 85: Testing Audiovisual filmmaKer's intEnt across 85 Hours of Film taaft Films communicate through deliberate creative choices, including lighting, color, composition, edit… 2026-08-30 published
  22. TalkFa: A Unified Benchmark for Farsi Dialogue Generation and Understanding taaft Farsi, spoken by more than 120 million people, lacks a comprehensive benchmark for dialogue generat… 2026-09-01 published
  23. TAME: Temporal-Aware Mixture-of-Experts for Text-Video Retrieval taaft Text-Video Retrieval (TVR) retrieves videos that match a natural-language query, but extending imag… 2026-09-02 published
  24. TAMI: Temporally Aligned, Missingness-Aware, and Interpretable Multimodal Fusion for Mental Health Assessment in Older Adults with Mild Cognitive Impairment taaft Depression and anxiety in older adults with Mild Cognitive Impairment (MCI) are frequently underdia… 2026-08-31 published
  25. TAPVid-MV: A Benchmark for Tracking Any Point in 3D Across Multiple Views taaft Multi-camera systems are increasingly practical for robotics, AR/VR, and autonomous driving because… 2026-09-01 published
  26. TaRA: Training-Aware Low-Rank Adaptation Initialization taaft Low-Rank Adaptation (LoRA) has become a de facto standard for parameter-efficient fine-tuning (PEFT… 2026-09-02 published
  27. Target-Aware State-Adaptive $p$-Dirichlet Graph Neural Regression for Non-Invasive Body-Composition Estimation taaft Accurate estimation of body-composition outcomes, including body fat percentage (BFP), bone mineral… 2026-08-30 published
  28. Task-Level Natural Language Priors as Learning Signals for Low-Resource LLM Training taaft Large language models (LLMs) often struggle when low-resource training data are ambiguous or incomp… 2026-09-02 published
  29. TC-Next: Zero-Shot Multimodal Cyclone Forecasting taaft We present TropicalCycloneNext (TC-Next), a multimodal deep learning model that forecasts tropical… 2026-09-02 published
  30. TDDM-Melatt: A Decoupled Memory and Diffusion Framework for Generalizable Encrypted Traffic Classification taaft The widespread adoption of encrypted traffic poses severe challenges to current security situationa… 2026-08-31 published
  31. TDFNet: Tri-projection Deformable Fusion Network for Panoramic Salient Object Detection taaft Recent years have witnessed the growing potential of panoramic salient object detection in robotic… 2026-08-26 published
  32. Technical Manual for a Toolkit for Measuring Contextual Individuation in Transformer Language Models taaft A transformer language model assigns a single, context-independent vector to a word type at its emb… 2026-09-04 published
  33. TempCloze: Can Video-LLMs Identify the Missing Middle? taaft Temporal reasoning benchmarks for Video-LLMs are often mediated by language, leaving room for lingu… 2026-09-01 published
  34. TempJail: Temporal Jailbreak Attacks against Image-to-Video Generation Models taaft In recent years, image-to-video (I2V) generation models have made remarkable progress in subject co… 2026-08-27 published
  35. Template-based Object Detection Using a Foundation Model taaft Most currently used object detection methods are learning-based, and can detect objects under varyi… 2026-03-20 published
  36. TEMPO: Temporally-grounded Multi-task Post-training for Large Audio-Language Models taaft Large audio-language models (LALMs) describe audio at the clip level but cannot assign timestamps t… 2026-08-30 published