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

Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech taaft Recently, denoising diffusion probabilistic models and generative score matching have shown high po… 2021-05-13 published
Gradient Descent with Projection Finds Over-Parameterized Neural Networks for Learning Low-Degree Polynomials with Nearly Minimax Optimal Rate taaft We study the problem of learning a low-degree spherical polynomial of degree $k_0 = Θ(1) \ge 1$ def… 2026-03-22 published
Gradient-Update Mismatch: Rethinking Conflict-Free Training of Physics-Informed Neural Networks taaft Training Physics-Informed Neural Networks (PINNs) requires jointly optimizing physics residual and… 2026-09-01 published
GRADSOLVE: fast exact gradients for ODE ensembles on GPUs taaft Ordinary differential equations (ODEs) underlie models in science and engineering, and many applica… 2026-09-02 published
GraFT: A Training-Free Framework for Spatial Reasoning in Multimodal Large Language Models via 3D Scene Graphs taaft 3D spatial reasoning underpins understanding and acting in the physical world, yet it remains unrel… 2026-09-03 published
GraftSR: Grafting Authentic Textures for Real-World Image Super-Resolution via Identical-Instance Guidance taaft Diffusion-based real-world image super-resolution (SR) achieves impressive perceptual quality but i… 2026-08-26 published
GRAIN: Bridging Name and Narrative Shifts in Real-World Graph Reasoning through Invariance-Rewarded Agentic RL taaft Despite their potential in standardized graph tasks, Large Language Models (LLMs) remain brittle to… 2026-08-27 published
GraM-Diff: A Unified Graph-Mamba Diffusion Framework for EEG-Based Alzheimer's Disease Data Generation and Diagnosis taaft Electroencephalography (EEG) is a promising, non-invasive, and cost-effective modality for Alzheime… 2026-08-30 published
Graph Machine: Towards Better Pretraining via Edges taaft We introduce the Graph Machine (GM), an architecture that maintains an $O(n)$-sized state and acces… 2026-09-02 published
Graph of Thoughts: Solving Elaborate Problems with Large Language Models Cledar We introduce Graph of Thoughts (GoT): a framework that advances prompting capabilities in large lan… 2023-08-18 published
Graph4BiLO: Graph Neural Network Approximation for Bilevel Mixed-Integer Linear Optimization taaft Bilevel mixed-integer linear optimization problems model hierarchical decision processes in which a… 2026-08-31 published
GraphGPT: Graph Instruction Tuning for Large Language Models taaft Graph Neural Networks (GNNs) have evolved to understand graph structures through recursive exchange… 2023-10-19 published
GraphMemix: Query-Aware Evidence Forests for Long-Term Multimodal Agent Memory taaft Organizing long-term memory for multimodal agents remains challenging because existing methods eith… 2026-08-27 published
GraspHOI: Full-Body 3D Human-Object Reconstruction with Finger-Level Grasps from a Single In-the-Wild Image taaft Existing monocular full-body 3D human-object interaction (HOI) methods do not combine explicit fing… 2026-08-28 published
Grounded, Compute-Efficient LLM Policy Agents for Energy-Poverty Equity in Physically-Constrained Peer-to-Peer Energy Markets taaft Energy poverty is nearly absent from NLP-for-social-good, and the little existing work is either st… 2026-09-01 published
Groundhog Bit-Flip Attack: Seeding Infinite Generation Loops in Mixture-of-Experts LLMs through Bit Flips taaft Mixture-of-Experts (MoE) architectures enable scalable and efficient large language models (LLMs) b… 2026-08-26 published
Group Adaptive Clipping Policy Optimization taaft Group relative policy optimization for reinforcement learning with verifiable rewards (RLVR) typica… 2026-08-31 published
Group-Shared Low-Rank Approximation for Mobile-Efficient Pointwise Convolutions in Large-Kernel CNNs taaft Large-kernel Convolutional Neural Networks (CNNs) deliver remarkable performance in vision tasks by… 2026-08-26 published
Group3D: MLLM-Driven Semantic Grouping for Open-Vocabulary 3D Object Detection taaft Open-vocabulary 3D object detection aims to localize and recognize objects beyond a fixed training… 2026-03-23 published
Grouped Query Experts: Mixture-of-Experts on GQA Self-Attention taaft Self-attention is central to Transformer performance and is often the most expensive part of the Tr… 2026-06-18 published
Guardrail-Agnostic Societal Bias Evaluation in Large Vision-Language Models taaft We propose a societal bias evaluation method for large vision-language models (LVLMs) in the era of… 2026-08-30 published
GUIDE: Generative Unsupervised Chinese Query Correction via Phonetic and Visual Shared-ID Encoding taaft Chinese query correction (CQC) is important for search and query recommendation on content platform… 2026-08-26 published
GUIDED: Granular Understanding via Identification, Detection, and Discrimination for Fine-Grained Open-Vocabulary Object Detection taaft Fine-grained open-vocabulary object detection (FG-OVD) aims to detect novel object categories descr… 2026-03-27 published
GUT: Quantifying and Optimizing the Reasoning Uncertainty of LLMs via Graph Complexity taaft Recent years have witnessed great advances in the reasoning ability of Large Language Models (LLMs)… 2026-09-04 published
H2Table: Hierarchical Hypergraph-Enhanced Large Language Models for Complex Table Reasoning taaft Tables are ubiquitous across diverse domains, yet reasoning over them remains a significant challen… 2026-09-01 published
H3-World: Turning Language Understanding into World Control taaft We present H3-World, an efficient framework that turns the 33B MiniMax-H3 video generator into an i… 2026-09-01 published
H3DNAS: Hardware-Aware ONNX-Native 3D Point Cloud Model Compression taaft Deploying 3D point cloud models on edge hardware such as the NVIDIA Jetson Orin Nano is severely co… 2026-09-02 published
Hallucination Mitigation for Large Vision-Language Models via Implicit Feature Stabilization taaft Large Vision-Language Models (LVLMs) are prone to hallucinations: they fluently describe objects, a… 2026-08-30 published
HalluPeer: A Taxonomy-driven Benchmark for Detecting Hallucinations in Scientific Peer Reviews taaft The growing scale of academic peer review has motivated the use of Large Language Models (LLMs) as… 2026-09-03 published
Hamiltonian Spectral-Temporal Dissipative Dynamics for Sequential Recommendation taaft Sequential recommendation requires understanding how user preferences evolve over time, yet most ex… 2026-08-26 published
HandVQA: Diagnosing and Improving Fine-Grained Spatial Reasoning about Hands in Vision-Language Models taaft Understanding the fine-grained articulation of human hands is critical in high-stakes settings such… 2026-03-27 published
Handwriting Trajectory Recovery via Autoregressive Ordered Stroke Instance Prediction taaft Handwriting trajectory recovery aims to infer the dynamic writing process hidden behind a static ha… 2026-09-02 published
Hardware-Accelerated Instance Segmentation for Resource-Constrained Space Robotics with Criticality Analysis taaft Autonomous lunar missions require real-time per- ception under three coupled constraints: extreme l… 2026-09-02 published
Hardware-Aware Tensor Networks for Real-Time Quantum-Inspired Anomaly Detection at Particle Colliders taaft Quantum machine learning offers the ability to capture complex correlations in high-dimensional fea… 2026-03-27 published
HarmoCore: Functional Latent Diffusion for Sparse Reconstruction of Oscillatory Wave Fields taaft Reconstructing oscillatory wave fields from scattered sensors is a severely underdetermined inverse… 2026-09-01 published
Harness Engineering in LLM Tool Use via Agent-Native Reusable Tool Primitives taaft Large language models (LLMs) augmented with external tools have demonstrated remarkable capability… 2026-09-01 published