Page 39 - Paper Library - AiPaper

Omnigrasp: Grasping Diverse Objects with Simulated Humanoids

Published:7/16/2024

Grasp Control with Simulated HumanoidsGrasping and Moving Diverse ObjectsHumanoid Motion Representation LearningTraining without Paired DatasetObject Trajectory Following Task

Omnigrasp is a method for controlling simulated humanoids to grasp and manipulate over 1200 diverse objects along predefined trajectories. It enhances control accuracy through humanoid motion representation, requiring no paired training data and demonstrating excellent scalabilit

Stable-Predictive Optimistic Counterfactual Regret Minimization

Published:2/14/2019

Counterfactual Regret MinimizationStable-Predictive Regret MinimizationLarge-Scale Game SolvingConvergence Rate OptimizationStability in Decision Trees

This paper introduces a new CFR variant achieving

O(T^{3/4})

convergence rate for largescale extensiveform games. By combining advances in predictive and stable regret minimization, the concept of 'stablepredictivity' enhances algorithm performance beyond traditional CFR.

Learning Smooth Humanoid Locomotion through Lipschitz-Constrained Policies

Published:10/16/2024

Lipschitz-Constrained PoliciesSmooth Locomotion Control for Legged RobotsReinforcement Learning and Sim-to-Real TransferDevelopment of Smooth Behaviors for RobotsLow-Pass Filtering and Smoothness Rewards

This paper introduces LipschitzConstrained Policies (LCP) to enhance humanoid robot locomotion control. LCP enforces smooth behaviors in a reinforcement learning framework, replacing traditional smoothing rewards, and integrates easily with automatic differentiation. Experiments

Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model

Published:10/14/2025

Vision-Language-Action ModelEnhanced Spatial Understanding CapabilitiesImplicit Spatial Representation AlignmentAlignment with 3D Foundation ModelsPrecise Execution of Robotic Tasks

This paper introduces 'Spatial Forcing' (SF), an implicit alignment method enhancing spatial understanding in VisionLanguageAction (VLA) models. By aligning visual embeddings with 3D foundation models, SF improves robotics' operational precision in 3D environments without relyi

$π_\texttt{RL}$: Online RL Fine-tuning for Flow-based Vision-Language-Action Models

Published:10/30/2025

Flow-based Vision-Language-Action ModelsOnline Reinforcement Learning Fine-TuningLIBERO BenchmarkMultitask Reinforcement LearningDenoising Modeling in Environment Interaction

The paper introduces the

π ext{RL}

framework, using online reinforcement learning to finetune flowbased VisionLanguageAction models, addressing challenges in action loglikelihoods. It demonstrates significant performance improvements on LIBERO and ManiSkill benchmarks.

ManiSkill-HAB: A Benchmark for Low-Level Manipulation in Home Rearrangement Tasks

Published:12/9/2024

Low-Level Manipulation BenchmarkIn-Home Object Rearrangement TasksReinforcement Learning and Imitation Learning BaselinesGPU-Accelerated Home Assistant BenchmarkData Generation and Demonstration Filtering

ManiSkillHAB introduces a benchmark for lowlevel manipulation in home rearrangement tasks, addressing the need for faster simulations and complex environments. It features GPU acceleration, enhanced speed, extensive reinforcement and imitation learning baselines, and a rulebas

DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization

Published:5/18/2025

RL Training for Large Language ModelsGroup Relative Policy OptimizationDiscriminative Constrained Optimization FrameworkLarge Reasoning ModelsEnhancement of Mathematical Reasoning Capabilities

DisCO is a new framework for Large Reasoning Models, addressing limitations of Group Relative Policy Optimization. By using a discriminative objective and nonclipping scoring functions, it eliminates difficulty bias and achieves stable longterm training, enhancing mathematical

Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention

Published:10/5/2025

Analysis of Low-Precision Transformer Training FailuresFlash Attention MechanismTraining Dynamics StabilityLow-Rank Representations and Bias ErrorsError Accumulation in Model Training

This paper explains the loss explosion in lowprecision transformer training as a result of lowrank representations and biased rounding errors, leading to a vicious cycle of error accumulation. A simple modification to Flash Attention stabilizes the training process.

014

Transformations in exposure to debris flows in post-earthquake Sichuan, China

Post-Earthquake Debris Flow ExposureDebris Flow Simulation and Assessment in SichuanImpact of Drainage Structures on Debris FlowsHigh-Resolution Satellite Imagery AnalysisUrban Development and Natural Disaster Interactions

This study examines how catchment interventions in three gullies in Sichuan, postearthquake, affect debris flow exposure. Findings indicate urban development increased the risk of a 2019 debris flow, and check dams effectively manage low and high flow events, but fail against ex

Distributed LLM Serving on Consumer-Grade GPUs by Reconciling Computation and Communication

Published:1/1/2025

Distributed LLM Serving on Consumer-Grade GPUsMoLink Serving SystemPrefill Request Transmission Scheduling AlgorithmCommunication Efficiency Optimization for LLMsDistributed Inference Computing Architecture

This paper presents MoLink, an efficient distributed LLM serving system that reduces costs using consumergrade GPUs. It splits the prefill request data into smaller chunks and optimizes transmission scheduling, achieving up to 46% reductions in firsttoken generation time, pert

Order-agnostic Identifier for Large Language Model-based Generative Recommendation

Published:2/15/2025

LLM-based Generative Recommendation SystemsOrder-Agnostic Identifier DesignIntegration of Collaborative Filtering and Semantic InformationSETRec FrameworkSparse Attention Mechanism

This paper presents an orderagnostic identifier design for LLMbased generative recommendations, addressing efficiency and performance issues. By integrating CF and semantic information using the SETRec framework, it significantly enhances recommendation effectiveness and genera

Comprehensive characterization and expression analysis of enzymatic antioxidant gene families in passion fruit (Passiflora edulis)

Published:10/26/2023

Identification of Antioxidant Enzyme Gene Families in Passion FrExpression Analysis of Antioxidant GenesCharacteristics of Antioxidant Enzyme Gene FamiliesTemperature Stress Resistance in Passion FruitSecondary Metabolite Research

This study identifies and characterizes 90 antioxidant genes in passion fruit, revealing phylogenetic links among similarly localized genes and their role in oxidative protection in flowers/fruits, while suggesting candidates for enhancing temperature stress resistance.

DexFlyWheel: A Scalable and Self-improving Data Generation Framework for Dexterous Manipulation

Published:9/28/2025

Data Generation for Dexterous ManipulationSelf-Improving Data Generation FrameworkImitation Learning and Reinforcement LearningData Diversity EnhancementIterative Cycle Data Generation

DexFlyWheel introduces a scalable and selfimproving data generation framework for dexterous manipulation, addressing the lack of diverse, highquality training datasets. Utilizing a closedloop pipeline with imitation learning, residual RL, and data augmentation, it iteratively

MoMaGen: Generating Demonstrations under Soft and Hard Constraints for Multi-Step Bimanual Mobile Manipulation

Published:10/21/2025

Multi-Step Bimanual Mobile Manipulation Demonstration GenerationImitation Learning for Robot TrainingConstraint-Based Optimization for Data GenerationAugmentation of Human Demonstration DatasetsReachability and Visibility Issues in Mobile Manipulation

MoMaGen introduces a method for generating demonstrations in multistep bimanual mobile manipulation, addressing the high cost of human data collection by solving base placement and visibility issues. The evaluation shows it greatly enhances dataset diversity compared to existing

ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning

Published:7/23/2025

Vision-Language-Action ReasoningReinforced Visual Latent PlanningMultimodal Large Language ModelLong-Horizon PlanningRobotic Action Execution

ThinkAct proposes a dualsystem framework that connects highlevel reasoning and lowlevel action execution through reinforced visual latent planning, enabling fewshot adaptation, longhorizon planning, and selfcorrection in complex environments.

Breaking the Bottleneck: User-Specific Optimization and Real-Time Inference Integration for Sequential Recommendation

Published:8/3/2025

Sequential Recommender SystemsUser-Specific OptimizationReal-Time Inference IntegrationKL Divergence OptimizationDeep Learning Sequence Methods

This paper addresses performance bottlenecks in sequential recommendation by proposing userspecific optimization, analyzing each user's behavior independently, and integrating realtime inference to enhance efficiency and model stability, using KL divergence for individual seque

Robust deep learning–based protein sequence design using ProteinMPNN

Published:9/15/2022

Deep Learning-Based Protein Sequence DesignProteinMPNNProtein Structure PredictionExperimental Protein Design MethodsMulti-Chain Amino Acid Coupling

The study introduces ProteinMPNN, a deep learningbased protein sequence design method, achieving 52.4% sequence recovery, outperforming Rosetta's 32.9%. It can handle amino acid coupling in single and multichains, successfully rescuing previously failed protein designs, showcas

015

Generative Sparse-View Gaussian Splatting

Published:6/10/2025

Generative Sparse-View Gaussian Splatting3D/4D Scene ReconstructionImage Diffusion ModelsView Consistency EnhancementGenerative Models for Limited Observations

The paper presents Generative Sparseview Gaussian Splatting (GSGS) to enhance 3D/4D scene reconstruction under limited observations, leveraging pretrained image diffusion models to improve view consistency and rendering quality, outperforming existing stateoftheart methods.

Personalized Safety in LLMs: A Benchmark and A Planning-Based Agent Approach

Published:5/25/2025

Personalized Safety in Large Language ModelsPENGUIN BenchmarkUser-Context-Based Safety EnhancementRAISE Agent FrameworkSafety Evaluation Methods

This paper introduces personalized safety and presents the PENGUIN benchmark, showing a 43.2% safety score improvement from personalized user information. It also develops the RAISE framework, enhancing safety scores by 31.6% without the need for model retraining, highlighting th

014

探究老年糖尿病夜间低血糖的预防及护理

Elderly Diabetes CareHypoglycemia Prevention MeasuresNighttime Hypoglycemia ManagementDiabetes Clinical Treatment

The paper explores the causes and nursing measures for nocturnal hypoglycemia in elderly diabetics, highlighting their diminished awareness. It presents six causes and five preventive strategies to guide clinical practitioners.

761 - 780 / 1082

Papers