Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks41 from public data
- 301
- Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail177
Alpamayo-R1 (AR1), a vision-language-action model (VLA) that integrates Chain of Causation reasoning with trajectory planning for complex driving scenarios, demonstrates a practical path towards Level 4 autonomous driving.
- 119
- 110
- Describe Anything: Detailed Localized Image and Video Captioning107
The Describe Anything Model (DAM), a model designed for detailed localized captioning (DLC), is introduced and sets new state-of-the-art on 7 benchmarks spanning keywordlevel, phrase-level, and detailed multi-sentence localized image and video captioning.
- A Semi-Supervised Two-Stage Approach to Learning from Noisy Labels107
This paper contends that it is actually better to ignore the labels of some of the data points than to keep them if the labels are incorrect, especially when the noisy rate is high, and suggests a two-stage framework for the learning from noisy labels.
- Learning Raw Image Denoising With Bayer Pattern Unification and Bayer Preserving Augmentation78
A Bayer pattern unification (BayerUnify) method to unify different Bayer patterns is proposed to fully utilize a heterogeneous dataset to train a single denoising model instead of training one model for each pattern.
- Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation75
Scenethesis is a training-free agentic framework that integrates LLM-based scene planning with vision-guided layout refinement and generates diverse, realistic, and physically plausible 3D interactive scenes, making it valuable for virtual content creation, simulation environments, and embodied AI research.
- Self-Supervised Learning for Audio-Visual Speaker Diarization38
This paper proposes a self-supervised audio-video synchronization learning method to address the problem of speaker diarization without massive labeling effort and improves the previous approaches by introducing two new loss functions: the dynamic triplet loss and the multinomial loss.
- ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediary33
ArtiScene is a training-free automated pipeline for scene design that integrates the flexibility of free-form text-to-image generation with the diversity and reliability of 2D intermediary layouts, and outperforms state-of-the-art benchmarks by a large margin in layout and aesthetic quality by quantitative metrics.
- Deep Learning for Classifying of White Blood Cancer30
This team deploys several state-of-the-art CNN architectures and uses an ensemble method named stacking to boost the final prediction performance, which helped to get the eighth place in the preliminary phase and tenth place inThe final phase of the C-NMC challenge.
- Citations and Trust in LLM Generated Responses24
A significant increase in trust was found when citations were present, a result that held true even when the citations were random; a significant decrease was found when participants checked the citations, highlighting the importance of citations in enhancing trust in AI-generated content.
- Defending Against Adversarial Attacks Using Random Forest24
This paper proposes to use a simple yet very effective non-differentiable hybrid model that combines DNNs and random forests, rather than hide gradients from attackers, to defend against the attacks.
- 11
- GenUSD: 3D scene generation made easy10
GenUSD is introduced, an end-to-end text-to-scene generation framework that transforms natural language queries into realistic 3D scenes, including 3D objects and layouts, and introduces object layout design meta functions as tools for the LLM.
- Non-Invasive Load Identification Algorithm Based on Color Coding and Feature Fusion of Power and Current10
The testing results on the PLAID data set indicate that in comparison with the traditional load identification algorithm, the algorithm proposed in this study performs higher identification accuracy with a smaller neural network parameter scale, which significantly improves the identification efficiency.
- 10
- 8
- 8
- 7
- Polylactic acid microplastics and fish species intestinal inflammation risk: Associated with mitochondrial function mediated by Sesn2/Nrf2 pathway5
Findings reveal a specific molecular pathway for PLA MPs to induce intestinal damage, which will contribute to assessing the ecological risks of BMPs to aquatic organisms.
- 5
- 3
- [Retracted] A Lightweight Face Verification Based on Adaptive Cascade Network and Triplet Loss Function3
A face verification framework based on adaptive cascade network and triplet loss that achieves a classification accuracy of 99.2% on the dataset of Labeled Faces in the Wild and shows the computation efficiency of the proposed framework.
- Identity Lock: Locking API Fine-tuned LLMs With Identity-based Wake Words2
This paper introduces a novel mechanism called identity lock, which restricts the model's core functionality until it is activated by specific identity-based wake words, such as "Hey! [Model Name]!".
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-15. 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.