1 citations · 1 across the 20 of their papers we have counts for
22 papers
Alleviating Hallucination in Reasoning Tasks with Training-Free Uncertainty-Guided Steering
Litian Liu, Qiqi Hou, Yubing Jian +5
Recent work on hallucination detection in large language models has shown that, for a fixed pre-trained model and reasoning task, it is possible to estimate the model's confidence…
CLEAR: Closed-Loop Reinforcement Learning at Scale for End-to-End Autonomous Driving
Yunxiao Shi, Hong Cai, Mohammad Ghavamzadeh +1
End-to-end autonomous driving (E2E-AD) aims to directly map raw sensor information to driving actions. Recently, with the rapid advancement of multi-modal large language models (ML…
MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving
Rajeev Yasarla, Deepti Hegde, Hsin-Pai Cheng +9
Vision-language-action (VLA) models are effective as end-to-end motion planners, but can be brittle when evaluated in closed-loop settings due to being trained under traditional im…
Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model
Tao Lin, Yuxin Du, Jiting Liu +14
Vision-Language-Action models have emerged as a promising paradigm for robotic manipulation by unifying perception, language grounding, and action generation. However, they often s…
CoReDiT: Spatial Coherence-Guided Token Pruning and Reconstruction for Efficient Diffusion Transformers
Zhuojin Li, Hsin-Pai Cheng, Hong Cai +2
Diffusion Transformers (DiTs) deliver remarkable image and video generation quality but incur high computational cost, limiting scalability and on-device deployment. We introduce C…
HLA: Hadamard Linear Attention
Hanno Ackermann, Hong Cai, Mohsen Ghafoorian +1
The attention mechanism is an important reason for the success of transformers. It relies on computing pairwise relations between tokens. To reduce the high computational cost of s…
Double-P: Hierarchical Top-P Sparse Attention for Long-Context LLMs
Wentao Ni, Kangqi Zhang, Zhongming Yu +7
As long-context inference becomes central to large language models (LLMs), attention over growing key-value caches emerges as a dominant decoding bottleneck, motivating sparse atte…
Generative Scenario Rollouts for End-to-End Autonomous Driving
Rajeev Yasarla, Deepti Hegde, Shizhong Han +10
Vision-Language-Action (VLA) models are emerging as highly effective planning models for end-to-end autonomous driving systems. However, current works mostly rely on imitation lear…
Myosotis: structured computation for attention like layer
Evgenii Egorov, Hanno Ackermann, Markus Nagel +1
Attention layers apply a sequence-to-sequence mapping whose parameters depend on the pairwise interactions of the input elements. However, without any structural assumptions, memor…
ODG: Occupancy Prediction Using Dual Gaussians
Yunxiao Shi, Yinhao Zhu, Shizhong Han +4
Occupancy prediction infers fine-grained 3D geometry and semantics from camera images of the surrounding environment, making it a critical perception task for autonomous driving. E…
DySS: Dynamic Queries and State-Space Learning for Efficient 3D Object Detection from Multi-Camera Videos
Rajeev Yasarla, Shizhong Han, Hong Cai +1
Camera-based 3D object detection in Bird's Eye View (BEV) is one of the most important perception tasks in autonomous driving. Earlier methods rely on dense BEV features, which are…
RoCA: Robust Cross-Domain End-to-End Autonomous Driving
Rajeev Yasarla, Shizhong Han, Hsin-Pai Cheng +7
End-to-end (E2E) autonomous driving has recently emerged as a new paradigm, offering significant potential. However, few studies have looked into the practical challenge of deploym…
BePo: Dual Representation for 3D Occupancy Prediction
Yunxiao Shi, Hong Cai, Jisoo Jeong +4
3D occupancy infers fine-grained 3D geometry and semantics which is critical for autonomous driving. Most existing approaches carry high compute costs, requiring dense 3D feature v…
FALO: Fast and Accurate LiDAR 3D Object Detection on Resource-Constrained Devices
Shizhong Han, Hsin-Pai Cheng, Hong Cai +3
Existing LiDAR 3D object detection methods predominantely rely on sparse convolutions and/or transformers, which can be challenging to run on resource-constrained edge devices, due…
H3O: Hyper-Efficient 3D Occupancy Prediction with Heterogeneous Supervision
Yunxiao Shi, Hong Cai, Amin Ansari +1
3D occupancy prediction has recently emerged as a new paradigm for holistic 3D scene understanding and provides valuable information for downstream planning in autonomous driving.…
Distilling Multi-modal Large Language Models for Autonomous Driving
Deepti Hegde, Rajeev Yasarla, Hong Cai +7
Autonomous driving demands safe motion planning, especially in critical "long-tail" scenarios. Recent end-to-end autonomous driving systems leverage large language models (LLMs) as…
PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer
Pierre-David Letourneau, Manish Kumar Singh, Hsin-Pai Cheng +6
We present Polynomial Attention Drop-in Replacement (PADRe), a novel and unifying framework designed to replace the conventional self-attention mechanism in transformer models. Not…
ToSA: Token Selective Attention for Efficient Vision Transformers
Manish Kumar Singh, Rajeev Yasarla, Hong Cai +2
In this paper, we propose a novel token selective attention approach, ToSA, which can identify tokens that need to be attended as well as those that can skip a transformer layer. M…
SciFlow: Empowering Lightweight Optical Flow Models with Self-Cleaning Iterations
Jamie Menjay Lin, Jisoo Jeong, Hong Cai +3
Optical flow estimation is crucial to a variety of vision tasks. Despite substantial recent advancements, achieving real-time on-device optical flow estimation remains a complex ch…
OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation
Jisoo Jeong, Hong Cai, Risheek Garrepalli +3
The scarcity of ground-truth labels poses one major challenge in developing optical flow estimation models that are both generalizable and robust. While current methods rely on dat…
DeCoTR: Enhancing Depth Completion with 2D and 3D Attentions
Yunxiao Shi, Manish Kumar Singh, Hong Cai +1
In this paper, we introduce a novel approach that harnesses both 2D and 3D attentions to enable highly accurate depth completion without requiring iterative spatial propagations. S…
FutureDepth: Learning to Predict the Future Improves Video Depth Estimation
Rajeev Yasarla, Manish Kumar Singh, Hong Cai +6
In this paper, we propose a novel video depth estimation approach, FutureDepth, which enables the model to implicitly leverage multi-frame and motion cues to improve depth estimati…