← Search

Jiayi Chen

43 accepted papers

2026

Compositional Attribute Imbalance in Vision Datasets

AAAI 2026technical

Visual attribute imbalance is a common yet underexplored issue in image classification, significantly impacting model performance and generalization. In this work, we first define the first-level and second-level attributes of images and then introduce a CLIP-based framework to construct a visual at

Cited by 0SourcePDFScholar
2026

Emerging Extrinsic Dexterity in Cluttered Scenes via Dynamics-aware Policy Learning

RSS 2026poster

Extrinsic dexterity leverages environmental contact to overcome the limitations of prehensile manipulation. However, achieving such dexterity in cluttered scenes remains challenging and underexplored, as it requires selectively exploiting contact among multiple interacting objects with inherently co…

Cited by 0SourceScholar
2026

LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion

RSS 2026poster

Recent robot foundation models largely rely on large-scale behavior cloning, which imitates expert actions but discards transferable dynamics knowledge embedded in heterogeneous embodied data. While the Unified World Model (UWM) formulation has the potential to leverage such diverse data, existing i…

Cited by 0SourceScholar
2026

MARS: A Meta-Adaptive Reinforcement Learning Framework for Risk-Aware Multi-Agent Portfolio Management

AAAI 2026technical

Reinforcement Learning (RL) has shown significant promise in automated portfolio management; however, effectively balancing risk and return remains a central challenge, as many models fail to adapt to dynamically changing market conditions. We propose Meta-controlled Agents for a Risk-aware System (

Cited by 0SourcePDFScholar
2026

ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver

AAAI 2026technical

Recent advances in Vision-Language-Action (VLA) models have enabled robotic agents to integrate multimodal understanding with action execution. However, our empirical analysis reveals that current VLAs struggle to allocate visual attention to target regions. Instead, visual attention is always dispe

Cited by 0SourcePDFScholar
2026

Rethinking the Practicality of Vision-Language-Action Model: A Comprehensive Benchmark and an Improved Baseline

ICRA 2026poster

Vision-Language-Action (VLA) models have emerged as a generalist robotic agent. However, existing VLAs are hindered by excessive parameter scales, prohibitive pre-training requirements, and limited applicability to diverse embodiments. To improve the practicality of VLAs, we propose a comprehensive …

2026

Robust Differentiable Collision Detection for General Objects

ICRA 2026poster

Collision detection is a core component of robotics applications such as simulation, control, and planning. Traditional algorithms like GJK+EPA compute textit{witness points}—the closest or deepest-penetration pairs between two objects—but are inherently non-differentiable, preventing gradient flow …

2026

Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Diffusion Diffusion Process

ICLR 2026poster

Vision-language-action (VLA) models aim to understand natural language instructions and visual observations and execute corresponding actions as an embodied agent. Recent advancements have integrated future images into the understanding-action loop, enabling foresight-driven policies that reduce abs…

Cited by 0SourcecodeScholar
2025

BODex: Scalable and Efficient Robotic Dexterous Grasp Synthesis Using Bilevel Optimization

ICRA 2025

Robotic dexterous grasping is important for interacting with the environment. To unleash the potential of data-driven models for dexterous grasping, a large-scale, highquality dataset is essential. While gradient-based optimization offers a promising way for constructing such datasets, previous work

Cited by 23SourcecodeScholar
2025

Bridging the Creativity Understanding Gap: Small-Scale Human Alignment Enables Expert-Level Humor Ranking in LLMs

EMNLP 2025

Large Language Models (LLMs) have shown significant limitations in understanding creative content, as demonstrated by Hessel et al. (2023)’s influential work on the New Yorker Cartoon Caption Contest (NYCCC). Their study exposed a substantial gap between LLMs and humans in humor comprehension, estab

Cited by 0SourcePDFScholar
2025

DexVLG: Dexterous Vision-Language-Grasp Model at Scale

ICCV 2025poster

As large models gain traction, vision-language models are enabling robots to tackle increasingly complex tasks. However, limited by the difficulty of data collection, progress has mainly focused on controlling simple gripper end-effectors. There is little research on functional grasping with large m…

Cited by 0SourcePDFScholar
2025

EvaLearn: Quantifying the Learning Capability and Efficiency of LLMs via Sequential Problem Solving

NeurIPS 2025poster

We introduce EvaLearn, a pioneering benchmark designed to evaluate large language models (LLMs) on their learning capability and efficiency in challenging tasks, a critical, yet underexplored aspect of model potential. EvaLearn contains 648 challenging problems across six task types, grouped into 18…

Cited by 0SourceScholar
2025

Geometric Knowledge-Guided Localized Global Distribution Alignment for Federated Learning

CVPR 2025poster

Data heterogeneity in federated learning, characterized by a significant misalignment between local and global distributions, leads to divergent local optimization directions and hinders global model training. Existing studies mainly focus on optimizing local updates or global aggregation, but these…

2025

GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data

CoRL 2025poster

Embodied foundation models are gaining increasing attention for their zero-shot generalization, scalability, and adaptability to new tasks through few-shot post-training. However, existing models rely heavily on real-world data, which is costly and labor-intensive to collect. Synthetic data offers a…

Cited by 0SourceScholar
2025

Lost in the Context: Insufficient and Distracted Attention to Contexts in Preference Modeling

ACL 2025long

In Reinforcement Learning from Human Feedback (RLHF), the reward model (RM) evaluates the response quality based on the given context and assigns a reward. It plays a crucial role in aligning RLHF with human preferences. Although the current RM training paradigm concatenates the context and response…

Cited by 0SourcePDFScholar
2025

Opportunistic Collaborative Planning with Large Vision Model Guided Control and Joint Query-Service Optimization

IROS 2025

Navigating autonomous vehicles in open scenarios is a challenge due to the difficulties in handling unseen objects. Existing solutions either rely on small models that struggle with generalization or large models that are resource-intensive. While collaboration between the two offers a promising sol

Cited by 1SourceScholar
2025

PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decoding

IROS 2025

Vision-Language-Action (VLA) models demonstrate remarkable potential for generalizable robotic manipulation. The performance of VLA models can be improved by integrating with action chunking, a critical technique for effective control. However, action chunking linearly scales up action dimensions in

Cited by 60SourceScholar
2025

PersLLM: A Personified Training Approach for Large Language Models

EMNLP 2025

Large language models (LLMs) exhibit human-like intelligence, enabling them to simulate human behavior and support various applications that require both humanized communication and extensive knowledge reserves. Efforts are made to personify LLMs with special training data or hand-crafted prompts, w

2025

Position: Iterative Online-Offline Joint Optimization is Needed to Manage Complex LLM Copyright Risks

ICML 2025poster

The infringement risks of LLMs have raised significant copyright concerns across different stages of the model lifecycle. While current methods often address these issues separately, this position paper argues that the LLM copyright challenges are inherently connected, and independent optimization o…

Cited by 0SourcePDFScholar
2025

PromptHash:Affinity-Prompted Collaborative Cross-Modal Learning for Adaptive Hashing Retrieval

CVPR 2025poster

Cross-modal hashing is a promising approach for efficient data retrieval and storage optimization. However, contemporary methods exhibit significant limitations in semantic preservation, contextual integrity, and information redundancy, which constrains retrieval efficacy. We present PromptHash, an…

2025

Pursuing Better Decision Boundaries for Long-Tailed Object Detection via Category Information Amount

ICLR 2025poster

In object detection, the number of instances is commonly used to determine whether a dataset follows a long-tailed distribution, implicitly assuming that the model will perform poorly on categories with fewer instances. This assumption has led to extensive research on category bias in datasets with…

Cited by 1SourcePDFScholar
2025

RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement

NAACL 2025long

Existing large language models (LLMs) show exceptional problem-solving capabilities but might struggle with complex reasoning tasks. Despite the successes of chain-of-thought and tree-based search methods, they mainly depend on the internal knowledge of LLMs to search over intermediate reasoning ste…

2025

RoboHanger: Learning Generalizable Robotic Hanger Insertion for Diverse Garments

RA-L 2025

For the task of hanging clothes, learning how to insert a hanger into a garment is a crucial step, but has rarely been explored in robotics. In this work, we address the problem of inserting a hanger into various unseen garments that are initially laid flat on a table. This task is challenging due t

Cited by 5SourceScholar
2024

Cross-Domain Few-Shot Semantic Segmentation via Doubly Matching Transformation

IJCAI 2024poster

Cross-Domain Few-shot Semantic Segmentation (CD-FSS) aims to train generalized models that can segment classes from different domains with a few labeled images. Previous works have proven the effectiveness of feature transformation in addressing CD-FSS. However, they completely rely on support image…

2024

D$^3$RoMa: Disparity Diffusion-based Depth Sensing for Material-Agnostic Robotic Manipulation

CoRL 2024poster

Depth sensing is an important problem for 3D vision-based robotics. Yet, a real-world active stereo or ToF depth camera often produces noisy and incomplete depth which bottlenecks robot performances. In this work, we propose D3RoMa, a learning-based depth estimation framework on stereo image pairs t…

Cited by 4SourceScholar
2024

DexGraspNet 2.0: Learning Generative Dexterous Grasping in Large-scale Synthetic Cluttered Scenes

CoRL 2024poster

Grasping in cluttered scenes remains highly challenging for dexterous hands due to the scarcity of data. To address this problem, we present a large-scale synthetic dataset, encompassing 1319 objects, 8270 scenes, and 426 million grasps. Beyond benchmarking, we also explore data-efficient learning s…

Cited by 10SourceScholar
2024

Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning

NeurIPS 2024spotlight

We present a novel multimodal preference dataset for creative tasks, consisting of over 250 million human votes on more than 2.2 million captions, collected through crowdsourcing rating data for The New Yorker's weekly cartoon caption contest over the past eight years. This unique dataset supports t…

2024

On Disentanglement of Asymmetrical Knowledge Transfer for Modality-Task Agnostic Federated Learning

AAAI 2024technical

There has been growing concern regarding data privacy during the development and deployment of Multimodal Foundation Models for Artificial General Intelligence (AGI), while Federated Learning (FL) allows multiple clients to collaboratively train models in a privacy-preserving manner. This paper form…

Cited by 9SourcePDFScholar
2024

Task-Oriented Dexterous Hand Pose Synthesis Using Differentiable Grasp Wrench Boundary Estimator

IROS 2024poster

This work tackles the problem of task-oriented dexterous hand pose synthesis, which involves generating a static hand pose capable of applying a task-specific set of wrenches to manipulate objects. Unlike previous approaches that focus solely on force-closure grasps, which are unsuitable for non-pre…

Cited by 1SourcecodeScholar
2024

Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shifts

CVPR 2024poster

Federated learning facilitates the collaborative learning of a global model across multiple distributed medical institutions without centralizing data. Nevertheless the expensive cost of annotation on local clients remains an obstacle to effectively utilizing local data. To mitigate this issue feder…

2023

DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation

ICRA 2023poster

Robotic dexterous grasping is the first step to enable human-like dexterous object manipulation and thus a crucial robotic technology. However, dexterous grasping is much more under-explored than object grasping with parallel grippers, partially due to the lack of a large-scale dataset. In this work…

Cited by 122SourcecodeScholar
2023

On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval

EMNLP 2023long findings

Visually-rich document entity retrieval (VDER), which extracts key information (e.g. date, address) from document images like invoices and receipts, has become an important topic in industrial NLP applications. The emergence of new document types at a constant pace, each with its unique entity types…

Cited by 0SourceScholar
2023

PartManip: Learning Cross-Category Generalizable Part Manipulation Policy From Point Cloud Observations

CVPR 2023poster

Learning a generalizable object manipulation policy is vital for an embodied agent to work in complex real-world scenes. Parts, as the shared components in different object categories, have the potential to increase the generalization ability of the manipulation policy and achieve cross-category obj…

Cited by 40SourcePDFScholar
2023

Tracking and Reconstructing Hand Object Interactions from Point Cloud Sequences in the Wild

AAAI 2023technical

In this work, we tackle the challenging task of jointly tracking hand object poses and reconstructing their shapes from depth point cloud sequences in the wild, given the initial poses at frame 0. We for the first time propose a point cloud-based hand joint tracking network, HandTrackNet, to estimat…

2023

UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy

CVPR 2023poster

In this work, we tackle the problem of learning universal robotic dexterous grasping from a point cloud observation under a table-top setting. The goal is to grasp and lift up objects in high-quality and diverse ways and generalize across hundreds of categories and even the unseen. Inspired by succe…

Cited by 119SourcePDFScholar
2022

Projective Manifold Gradient Layer for Deep Rotation Regression

CVPR 2022poster

Regressing rotations on SO(3) manifold using deep neural networks is an important yet unsolved problem. The gap between the Euclidean network output space and the non-Euclidean SO(3) manifold imposes a severe challenge for neural network learning in both forward and backward passes. While several wo…

Cited by 32PDFcodeScholar