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

Does Your Agent's Memory Survive a Model Upgrade? A Controlled Study of Memory Portability taaft Model upgrades are routine; memory migrations are not. An agent can keep the same memory store and… 2026-09-04 published
Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research taaft Information about pretraining corpora used to train the current best-performing language models is… 2024-01-31 published
Domain shift-robust object detection with GenAI image editing taaft Object detectors often degrade under domain shifts such as changes in lighting, weather, or occlusi… 2026-09-02 published
DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation taaft Open domain subject-driven text-to-video (S2V) generation has drawn significant interest in academi… 2026-06-24 published
Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and Inference taaft Layer dropout (a.k.a. stochastic depth) has been shown to enable faster training, higher accuracy,… 2026-09-04 published
Don't Drop the BATON: Long-Horizon Robot Manipulation via Agentic Subtask Exploration and Transition-aware Memory taaft Long-horizon robot manipulation chains many contact-rich skills into one multi-stage task. Vision-l… 2026-08-17 published
Don't Just Listen, Try Planning: Graph-based Retrieval-Generation Agent for Long-form Audio Meeting Understanding taaft While long-form audio meeting understanding (LAMU) is garnering growing attention, task-specific qu… 2026-08-25 published
Don't Mix Rewards, Mix Policies: Policy Decomposition and Optimization for Multi-Reward RL taaft Modern large language models (LLMs) are expected not just to answer correctly, but to adapt their b… 2026-07-31 published
Don't Vibe Code, Do Skele-Code: Interactive No-Code Notebooks for Subject Matter Experts to Build Lower-Cost Agentic Workflows taaft Skele-Code is a natural-language and graph-based interface for building workflows with AI agents, d… 2026-03-18 published
Door-in-the-Face Requests and Refusal Behaviour in Large Language Models taaft Does the door-in-the-face technique work on language models? In humans, a large request that is ref… 2026-09-02 published
DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining taaft The mixture proportions of pretraining data domains (e.g., Wikipedia, books, web text) greatly affe… 2023-05-17 published
Dota 2 with Large Scale Deep Reinforcement Learning OpenAI On April 13th, 2019, OpenAI Five became the first AI system to defeat the world champions at an esp… 2019-12-13 published
Dotting the Eye: An Intent-Driven Image Retouching Agent for Visual Focus Enhancement taaft Image retouching is commonly formulated as enhancing overall visual quality through color adjustmen… 2026-09-01 published
Double Coupling Architecture and Training Method for Optimization Problems of Differential Algebraic Equations with Parameters taaft Simulation and modeling are essential in product development, integrated into the design and manufa… 2026-03-24 published
DPA-I2P: Depth-Guided Projective Alignment for Image-to-Point-Cloud Registration in Autonomous Driving taaft Image-to-Point Cloud Registration aims to estimate the camera pose of a given image within a 3D sce… 2026-08-27 published
DPA: Decoupling Product-Agnostic Anomaly Representations for Zero-shot Anomaly Generation taaft Industrial anomaly detection benefits from anomaly samples, yet newly deployed products typically p… 2026-09-02 published
Dr. Claw: An AI Scientist Workspace for Vibe Research taaft Command-line coding agents (e.g., Claude Code, Gemini CLI) can already read and write files and sus… 2026-08-31 published
DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training taaft Reinforcement Learning from Verifiable Rewards works well when a task has a programmatic checker, b… 2026-09-03 published
DragMesh-2: Physically Plausible Dexterous Hand-Object Interaction with Articulated Objects taaft Dexterous interaction with articulated objects is important for household, assistive, and humanoid… 2026-06-13 published
DramaChain Bench: An End-to-End Benchmark for Short-Drama Generation taaft Commercial short-drama production follows a multi-stage chain: script, storyboard, keyframe imagery… 2026-09-01 published
DreamFusion: Text-to-3D using 2D Diffusion taaft Recent breakthroughs in text-to-image synthesis have been driven by diffusion models trained on bil… 2022-09-29 published
DreamTalk: When Emotional Talking Head Generation Meets Diffusion Probabilistic Models taaft Emotional talking head generation has attracted growing attention. Previous methods, which are main… 2023-12-15 published
DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution taaft Recent video generators often omit audio or synthesize it in a separate stage, limiting reciprocal… 2026-08-31 published
Drift Calibration in Geometric Eye Tracking Systems taaft Geometric eye trackers can provide the spatial accuracy required for gaze-based interaction and mul… 2026-08-30 published
Drift-Aware LLM Routing with Sparse Contexts and Shared Budgets taaft A multi-model language service must route each request while preserving workload-level budgets for… 2026-09-01 published
Drift-Aware Multimodal User Representation Learning via Multi-Scale Temporal Modeling and Sparse Mixture-of-Experts taaft Understanding user preferences from noisy and temporally evolving social media behaviors is fundame… 2026-08-26 published
Drive-HWM: Hierarchical World Models for Dynamic-Latent Guided Autonomous Driving taaft World models offer a promising paradigm for autonomous driving by predicting how traffic scenes may… 2026-09-03 published
Driving on Memory taaft End-to-end autonomous driving models plan future trajectories from raw sensor input. While earlier… 2026-08-31 published
DropClick: Semi-Automated One-Click Segmentation for Agricultural Robotic Data taaft Labelling vision datasets, especially for segmentation tasks, is a laborious and costly process tha… 2026-09-03 published
DRoPS: Dynamic 3D Reconstruction of Pre-Scanned Objects taaft Dynamic scene reconstruction from casual videos has seen recent remarkable progress. Numerous appro… 2026-03-25 published
DSAQuant: Denoising-Stage-Aligned Quantization-Aware Training for Video Generation taaft Video diffusion models (VDMs) have achieved impressive progress in text-to-video generation, but th… 2026-09-03 published
dTRPO: Trajectory Reduction in Policy Optimization of Diffusion Large Language Models taaft Diffusion Large Language Models (dLLMs) introduce a new paradigm for language generation, which in… 2026-03-19 published
Dual Consensus: Escaping from Spurious Majority in Unsupervised RLVR via Two-Stage Vote Mechanism Hi-Speed Group Current label-free RLVR approaches for large language models (LLMs), such as TTRL and Self-reward,… 2026-03-17 published
Dual-level Adaptation for Multi-Object Tracking: Building Test-Time Calibration from Experience and Intuition taaft Multiple Object Tracking (MOT) has long been a fundamental task in computer vision, with broad appl… 2026-03-23 published
Dual-Part Multi-Lateral Branched Network for Multi-Class Segmentation in Cardiovascular Catheterization Angiograms taaft Catheterisation image processing requires segmentation models that are fast, accurate and explainab… 2026-09-04 published
Dual-Space Knowledge Distillation with Key-Query Matching for Large Language Models with Vocabulary Mismatch taaft Large language models (LLMs) achieve state-of-the-art (SOTA) performance across language tasks, but… 2026-03-23 published