Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks46 from public data
- 1,176
- Deep learning in remote sensing scene classification: a data augmentation enhanced convolutional neural network framework285
A methodology to not only enhance the volume and completeness of training data for any remote sensing datasets, but also exploit the enhanced datasets to train a deep convolutional neural network that achieves state-of-the-art scene classification performance.
- 150
- 59
- 54
- 45
- How Does Disagreement Benefit Co-teaching?32
Empirical results on noisy versions of MNIST, CIFAR-10 and NEWS demonstrate that Co-teaching+ is much superior to the state-of-the-art methods in the robustness of trained deep models.
- Deep learning for vision-based micro aerial vehicle autonomous landing32
Experimental results validate that the proposed vision-based autonomous landing system is robust to landmark variability in different backgrounds and lighting situations.
- Pumpout: A Meta Approach for Robustly Training Deep Neural Networks with Noisy Labels18
A meta algorithm called Pumpout is proposed to overcome the problem of memorizing noisy labels by using scaled stochastic gradient ascent, which actively squeezes out the negative effects of noisy labels from the training model, instead of passively forgetting these effects.
- SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale17
SkillDAG is presented, which models inter-skill relationships as a typed directed graph and exposes it to an LLM agent as an inference-time, agent-callable structural retrieval interface, queried and evolved during execution rather than baked into a fixed retrieval pipeline.
- Co-sampling: Training Robust Networks for Extremely Noisy Supervision17
Free of the matrix estimation, a simple but robust learning paradigm called "Co-sampling" is presented, which can train deep networks robustly under extremely noisy labels and demonstrates that it trains deep learning models robustly.
- 12
- Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Tasks11
Experiments demonstrate that NSI consistently outperforms state-of-the-art baselines, empowering agents to self-evolve into architects of logic-grounded skills.
- POI Recommendation via Multi-Objective Adversarial Imitation Learning7
This paper introduces Multi-Objective Adversarial Imitation Recommender (MOAIR), a novel framework that integrates Generative Adversarial Imitation Learning with multi-objective to address the persistent problem of data sparsity and incompleteness in generative adversarial learning.
- Pumpout: A Meta Approach to Robust Deep Learning with Noisy Labels7
Pumpout is proposed as a meta approach to learning with noisy labels and an alternative to early stopping, and it is demonstrated via experiments that Pumpout robustifies two representative base learning methods, and the performance boost is often significant.
- 6
- HREB-CRF: Hierarchical Reduced-bias EMA for Chinese Named Entity Recognition5
HREB-CRF framework: Hierarchical Reduced-bias EMA with CRF amplifies word boundaries and pools long text gradients through exponentially fixed-bias weighted average of local and global hierarchical attention.
- USN: A Robust Imitation Learning Method against Diverse Action Noise5
A robust learning paradigm called USN (Uncertainty-aware Sample-selection with Negative learning), which first estimates the predictive uncertainty for all demonstration data and then selects samples with high loss based on the uncertainty measures based on the uncertainty measures.
- 5
- Calibration Is Not Control: Intervention Value for LLM-Agent Oversight4
These results suggest that LLM-agent oversight should move from calibrated risk scoring toward action-conditioned value estimation, and introduce prefix branching, a same-prefix counterfactual protocol that executes candidate actions from identical trajectory states.
- SA-VLA: Spatially-Aware Flow-Matching for Vision-Language-Action Reinforcement Learning4
SA-VLA is proposed, a spatially-aware RL adaptation framework that preserves spatial grounding during policy optimization by aligning representation learning, reward design, and exploration with task geometry, and employs a spatially-conditioned annealed exploration strategy tailored to flow-matching dynamics.
- Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration4
A novel imitation learning algorithm called Imitation Learning with Double Exploration (ILDE), which implements exploration in two aspects: optimistic policy optimization via an exploration bonus that rewards state-action pairs with high uncertainty to potentially improve the convergence to the expert policy and curiosity-driven exploration of the states that deviate from the demonstration trajectories to potentially yield beyond-expert performance.
- FM-IRL: Flow-Matching for Reward Modeling and Policy Regularization in Reinforcement Learning4
This work proposes to let a student policy with simple MLP structure explore the environment and be online updated via RL algorithm with a reward model, containing rich information of expert data distribution, to avoid the gradient instability of FM policies and enable efficient online exploration.
- Don't Blindly Trust It: How Unreliable Feedback Breaks Tool-Using LLM Agents3
It is shown that clean-tool gains can overstate tool value, and that matched no-feedback fallback controls are necessary for evaluating tool-augmented agents.
- Reflection-Driven Control for Trustworthy Code Agents3
Empirical results show that Reflection-Driven Control substantially improves the security and policy compliance of generated code while largely preserving functional correctness, with minimal runtime and token overhead, indicating that Reflection-Driven Control is a practical path toward trustworthy AI coding agents.
- 3
- Towards Backdoor-Based Ownership Verification for Vision-Language-Action Models2
This paper presents GuardVLA, the first backdoor-based ownership verification framework specifically designed for VLAs, which embeds a stealthy and harmless backdoor watermark into the protected model during training by injecting secret messages into embodied visual data.
- HBVLA: Pushing 1-Bit Post-Training Quantization for Vision-Language-Action Models2
The results show that HBVLA incurs only marginal success-rate degradation compared to the full-precision model, demonstrating robust deployability under tight hardware constraints, and provides a practical foundation for ultra-low-bit quantization of VLAs, enabling more reliable deployment on hardware-limited robotic platforms.
- Self-Adaptive Gamma Context-Aware SSM-based Model for Metal Defect Detection2
A Self-Adaptive Gamma Context-Aware SSM-based model (GCM-DET), integrating a Dynamic Gamma Correction (GC) module to enhance grayscale representation and optimize feature extraction for precise defect reconstruction.
- MCMC Based Generative Adversarial Networks for Handwritten Numeral Augmentation2
A novel data augmentation framework for handwritten numerals by incorporating the probabilistic learning and the generative adversarial learning is proposed, which is more computationally efficient than those based on 2-D images.
- STaR-Quant: State-Time Consistent Post-Training Quantization for Diffusion Large Language Models1
STaR-Quant, a state-time consistent PTQ framework for DLLMs, introduces State-Guided Activation Transformation (SGAT) to assign masked and unmasked tokens to different activation transformation spaces with a unified static weight-side transformation.
- 1
- 1
- –
- –
- Advancing Analytic Class-Incremental Learning through Vision-Language Calibration–
A novel dual-branch framework that advances analytic CIL via a two-level vision-language calibration strategy that coherently fuse plastic, task-adapted features with a frozen, universal visual anchor at the feature level through geometric calibration, which maintains analytic-learning's extreme efficiency while overcoming its inherent brittleness.
- Adversarial Dual On-Policy Distillation from Expressive Teacher–
FA-OPD is proposed, an adversariesarial dual on-policy distillation method in which a Flow Matching teacher is learned from demonstrations and co-trained with a lightweight MLP student, and provides two complementary signals on student rollouts.
- –
- –
- –
- –
- –
- –
- –
- –
- Learning Efficient Planning-based Rewards for Imitation Learning–
A novel reward learning method is proposed, which streamlines a differential planning module with dynamics modeling that can outperform state-of-the-art IRL methods on multiple Atari games and continuous control tasks.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar; position from the scholar’s ORCID record, last synced 2026-10-10. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it. You will be asked to sign in.