arXiv subjects

Feng Tao

Publications and source records attributed to Feng Tao.

At least 19 recordsLinked to original sources

arXiv2026

Scaling Curriculum Learning For Autonomous Driving

Batched simulators for autonomous driving have recently enabled training reinforcement learning (RL) agents at scale, encompassing thousands of traffic scenarios and billions of interactions within a matter of days. Although such high-throughput feeds RL algorithms faster than ever, their sample-efficiency has not kept pace: As the standard training scheme, domain randomization uniformly samples scenarios, thereby consuming a vast number of interactions on cases that contribute little to learning. Curriculum learning offers a remedy by adaptively prioritizing scenarios that matter most to policy improvement. We present CL4AD, the first integration of curriculum learning into batched autonomous driving simulators by framing scenario selection as an unsupervised environment design problem. We introduce utility functions that shape curricula based on success rates and the realism of the agent's behavior, in addition to existing regret-estimation functions. Large-scale experiments in GPUDRIVE demonstrate that curriculum learning achieves a 99% success rate a billion steps earlier than domain randomization, reducing wall-clock time by 77%, and outperforms heuristic curricula with static and dynamic attributes, with only one exception at the largest scale. An ablation under limited compute shows that curriculum learning improves sample efficiency by 67%. We also investigate how utility functions behave at scale, and how prioritized scenarios evolve during training. We release an implementation of CLForAD in GPUDRIVE.

cs.AI↗

arXiv2026

Adapting Reinforcement Learning for Path Planning in Constrained Parking Scenarios

Real-time path planning in constrained environments remains a fundamental challenge for autonomous systems. Traditional classical planners, while effective under perfect perception assumptions, are often sensitive to real-world perception constraints and rely on online search procedures that incur high computational costs. In complex surroundings, this renders real-time deployment prohibitive. To overcome these limitations, we introduce a Deep Reinforcement Learning (DRL) framework for real-time path planning in parking scenarios. In particular, we focus on challenging scenes with tight spaces that require a high number of reversal maneuvers and adjustments. Unlike classical planners, our solution does not require ideal and structured perception, and in principle, could avoid the need for additional modules such as localization and tracking, resulting in a simpler and more practical implementation. Also, at test time, the policy generates actions through a single forward pass at each step, which is lightweight enough for real-time deployment. The task is formulated as a sequential decision-making problem grounded in a bicycle model dynamics, enabling the agent to directly learn navigation policies that respect vehicle kinematics and environmental constraints in the closed-loop setting. A new benchmark is developed to support both training and evaluation, capturing diverse and challenging scenarios. Our approach achieves state-of-the-art success rates and efficiency, surpassing classical planner baselines by +96% in success rate and +52% in efficiency. Furthermore, we release our benchmark as an open-source resource for the community to foster future research in autonomous systems. The benchmark and accompanying tools are available at https://github.com/dqm5rtfg9b-collab/Constrained_Parking_Scenarios.

cs.RO↗

arXiv2026

AntibodyDesignBFN: High-Fidelity Fixed-Backbone Antibody Design via Discrete Bayesian Flow Networks

The computational design of antibodies with high specificity and affinity is a cornerstone of modern therapeutic development. While deep generative models have demonstrated potential, they often struggle to balance high-fidelity geometric conditioning with the discrete nature of amino acid sequences. In this work, we present AntibodyDesignBFN, a novel framework for fixed-backbone antibody design based on Discrete Bayesian Flow Networks (BFN). Unlike standard diffusion models, BFNs operate on a continuous probability simplex, enabling a fully differentiable generative process that seamlessly integrates geometric gradients. By combining a lightweight Geometric Transformer with Invariant Point Attention (IPA) and a resource-efficient training strategy, our model establishes a new state-of-the-art. Evaluations on a rigorous 2025 temporal test set (43 complexes) demonstrate that AntibodyDesignBFN achieves an unprecedented Amino Acid Recovery(AAR) of 67.8%, significantly outperforming leading graph-based baselines. Furthermore, the model is highly efficient, enabling millisecond-scale inference on consumer-grade hardware. AntibodyDesignBFN thus offers a powerful, accessible, and mathematically robust framework for next generation antibody engineering. Code and model checkpoints are available at https://github.com/YueHuLab/AntibodyDesignBFN and https://huggingface.co/YueHuLab/AntibodyDesignBFN.

q-bio.QM↗

arXiv2025

Predicting the Thermal Conductivity Collapse in SWCNT Bundles: The Interplay of Symmetry Breaking and Scattering Revealed by Machine-Learning-Driven Quantum Transport

We combine machine learning (ML)-based neuroevolution potentials (NEP) with anharmonic lattice dynamics and the Boltzmann transport equation (ALD-BTE) to achieve a quantitative and mode-resolved description of thermal transport in individual (10, 0) zigzag single-walled carbon nanotubes (SWCNTs) and their bundles. Our analysis reveals a dual mechanism behind the drastic suppression of thermal conductivity in bundles: first, the breaking of rotational symmetry in isolated SWCNTs dramatically enhances the scattering rates of symmetry-sensitive phonon modes, such as the twist (TW) mode. Second, the emergence of new inter-tube phonon modes introduces abundant additional scattering channels across the entire frequency spectrum. Crucially, the incorporation of quantum Bose-Einstein (BE) statistics is essential to accurately capture these phenomena, enabling our approach to quantitatively reproduce experimental observations. This work establishes the combination of ML-driven interatomic potentials and ALD-BTE as a predictive framework for nanoscale thermal transport, effectively bridging the gap between theoretical models and experimental measurements.

cond-mat.mes-hall↗

arXiv2025

VideoPro: Adaptive Program Reasoning for Long Video Understanding

Large language models (LLMs) have shown promise in generating program workflows for visual tasks. However, previous approaches often rely on closed-source models, lack systematic reasoning, and struggle with long-form video question answering (videoQA). To address these challenges, we introduce the FS-VisPR framework, an adaptive visual program reasoning approach that balances fast reasoning for simple queries with slow reasoning for difficult ones. First, we design efficient visual modules (e.g., key clip retrieval and subtitle retrieval) to support long-form video tasks. Then, we construct a diverse and high-quality fast-slow reasoning dataset with a strong LLM to align open-source language models' ability to generate visual program workflows as FS-LLM. Next, we design a fast-slow reasoning framework with FS-LLM: Simple queries are directly solved by VideoLLMs, while difficult ones invoke visual program reasoning, motivated by human-like reasoning processes. During this process, low-confidence fast-thinking answers will trigger a second-stage slow-reasoning process, and a fallback mechanism to fast reasoning is activated if the program execution fails. Moreover, we improve visual programs through parameter search during both training and inference. By adjusting the parameters of the visual modules within the program, multiple variants are generated: during training, programs that yield correct answers are selected, while during inference, the program with the highest confidence result is applied. Experiments show that FS-VisPR improves both efficiency and reliability in visual program workflows. It achieves 50.4% accuracy on LVBench, surpassing GPT-4o, matching the performance of Qwen2.5VL-72B on VideoMME.

cs.CV↗

arXiv2025

End-to-End Visual Autonomous Parking via Control-Aided Attention

Precise parking requires an end-to-end system where perception adaptively provides policy-relevant details - especially in critical areas where fine control decisions are essential. End-to-end learning offers a unified framework by directly mapping sensor inputs to control actions, but existing approaches lack effective synergy between perception and control. Instead, we propose CAA-Policy, an end-to-end imitation learning system that allows control signal to guide the learning of visual attention via a novel Control-Aided Attention (CAA) mechanism. We train such an attention module in a self-supervised manner, using backpropagated gradients from the control outputs instead of from the training loss. This strategy encourages attention to focus on visual features that induce high variance in action outputs, rather than merely minimizing the training loss - a shift we demonstrate leads to a more robust and generalizable policy. To further strengthen the framework, CAA-Policy incorporates short-horizon waypoint prediction as an auxiliary task to improve temporal consistency of control outputs, a learnable motion prediction module to robustly track target slots over time, and a modified target tokenization scheme for more effective feature fusion. Extensive experiments in the CARLA simulator show that CAA-Policy consistently surpasses both the end-to-end learning baseline and the modular BEV segmentation + hybrid A* pipeline, achieving superior accuracy, robustness, and interpretability. Code and Collected Training datasets will be released. Code is released at https://github.com/ai4ce/CAAPolicy.

cs.CV↗

arXiv2025

Scientifically-Interpretable Reasoning Network (ScIReN): Discovering Hidden Relationships in the Carbon Cycle and Beyond

Soils have potential to mitigate climate change by sequestering carbon from the atmosphere, but the soil carbon cycle remains poorly understood. Scientists have developed process-based models of the soil carbon cycle based on existing knowledge, but they contain numerous unknown parameters and often fit observations poorly. On the other hand, neural networks can learn patterns from data, but do not respect known scientific laws, and are too opaque to reveal novel scientific relationships. We thus propose Scientifically-Interpretable Reasoning Network (ScIReN), a fully-transparent framework that combines interpretable neural and process-based reasoning. An interpretable encoder predicts scientifically-meaningful latent parameters, which are then passed through a differentiable process-based decoder to predict labeled output variables. While the process-based decoder enforces existing scientific knowledge, the encoder leverages Kolmogorov-Arnold networks (KANs) to reveal interpretable relationships between input features and latent parameters, using novel smoothness penalties to balance expressivity and simplicity. ScIReN also introduces a novel hard-sigmoid constraint layer to restrict latent parameters into prior ranges while maintaining interpretability. We apply ScIReN on two tasks: simulating the flow of organic carbon through soils, and modeling ecosystem respiration from plants. On both tasks, ScIReN outperforms or matches black-box models in predictive accuracy, while greatly improving scientific interpretability -- it can infer latent scientific mechanisms and their relationships with input features.

cs.LG↗

arXiv2025

Advanced Long-term Earth System Forecasting

Reliable long-term forecasting of Earth system dynamics is fundamentally limited by instabilities in current artificial intelligence (AI) models during extended autoregressive simulations. These failures often originate from inherent spectral bias, leading to inadequate representation of critical high-frequency, small-scale processes and subsequent uncontrolled error amplification. Inspired by the nested grids in numerical models used to resolve small scales, we present TritonCast. At the core of its design is a dedicated latent dynamical core, which ensures the long-term stability of the macro-evolution at a coarse scale. An outer structure then fuses this stable trend with fine-grained local details. This design effectively mitigates the spectral bias caused by cross-scale interactions. In atmospheric science, it achieves state-of-the-art accuracy on the WeatherBench 2 benchmark while demonstrating exceptional long-term stability: executing year-long autoregressive global forecasts and completing multi-year climate simulations that span the entire available $2500$-day test period without drift. In oceanography, it extends skillful eddy forecast to $120$ days and exhibits unprecedented zero-shot cross-resolution generalization. Ablation studies reveal that this performance stems from the synergistic interplay of the architecture's core components. TritonCast thus offers a promising pathway towards a new generation of trustworthy, AI-driven simulations. This significant advance has the potential to accelerate discovery in climate and Earth system science, enabling more reliable long-term forecasting and deeper insights into complex geophysical dynamics.

cs.LG↗

arXiv2025

BEVDiffuser: Plug-and-Play Diffusion Model for BEV Denoising with Ground-Truth Guidance

Bird's-eye-view (BEV) representations play a crucial role in autonomous driving tasks. Despite recent advancements in BEV generation, inherent noise, stemming from sensor limitations and the learning process, remains largely unaddressed, resulting in suboptimal BEV representations that adversely impact the performance of downstream tasks. To address this, we propose BEVDiffuser, a novel diffusion model that effectively denoises BEV feature maps using the ground-truth object layout as guidance. BEVDiffuser can be operated in a plug-and-play manner during training time to enhance existing BEV models without requiring any architectural modifications. Extensive experiments on the challenging nuScenes dataset demonstrate BEVDiffuser's exceptional denoising and generation capabilities, which enable significant enhancement to existing BEV models, as evidenced by notable improvements of 12.3\% in mAP and 10.1\% in NDS achieved for 3D object detection without introducing additional computational complexity. Moreover, substantial improvements in long-tail object detection and under challenging weather and lighting conditions further validate BEVDiffuser's effectiveness in denoising and enhancing BEV representations.

cs.CV↗

arXiv2025

Biogeochemistry-Informed Neural Network (BINN) for Improving Accuracy of Model Prediction and Scientific Understanding of Soil Organic Carbon

The increasing availability of large-scale observational data and the rapid development of artificial intelligence (AI) provide unprecedented opportunities to enhance our understanding of the global carbon cycle and other biogeochemical processes. However, retrieving mechanistic knowledge from these large-scale data remains a challenge. Here, we develop a Biogeochemistry-Informed Neural Network (BINN) that seamlessly integrates a vectorized process-based soil carbon cycle model (i.e., Community Land Model version 5, CLM5) into a neural network (NN) structure to examine mechanisms governing soil organic carbon (SOC) storage from big data. BINN demonstrates high accuracy in retrieving biogeochemical parameter values from synthetic data in a parameter recovery experiment. Furthermore, by incorporating Monte Carlo (MC) dropout to generate posterior distributions, we demonstrate that BINN can effectively quantify uncertainty in estimated parameters. We use BINN to predict six major processes (or components in process-based models) regulating the soil carbon cycle from 25,925 observed SOC profiles across the contiguous US and compare them with the same processes previously retrieved by a Bayesian inference-based PROcess-guided deep learning and DAta-driven modeling (PRODA) approach. The good agreement between the spatial patterns retrieved by BINN and PRODA (average correlation coefficient = 0.86) suggests that BINN's ability of capturing mechanistic knowledge is consistent with the established Bayesian-based methods. Additionally, the integration of neural networks and process-based models in BINN improves computational efficiency by more than 50 times over PRODA. We conclude that BINN is an efficient framework that harnesses the power of both AI, large-scale data, and process-based modeling to understand large scale soil carbon cycle.

physics.geo-ph↗

arXiv2025

AdaWM: Adaptive World Model based Planning for Autonomous Driving

World model based reinforcement learning (RL) has emerged as a promising approach for autonomous driving, which learns a latent dynamics model and uses it to train a planning policy. To speed up the learning process, the pretrain-finetune paradigm is often used, where online RL is initialized by a pretrained model and a policy learned offline. However, naively performing such initialization in RL may result in dramatic performance degradation during the online interactions in the new task. To tackle this challenge, we first analyze the performance degradation and identify two primary root causes therein: the mismatch of the planning policy and the mismatch of the dynamics model, due to distribution shift. We further analyze the effects of these factors on performance degradation during finetuning, and our findings reveal that the choice of finetuning strategies plays a pivotal role in mitigating these effects. We then introduce AdaWM, an Adaptive World Model based planning method, featuring two key steps: (a) mismatch identification, which quantifies the mismatches and informs the finetuning strategy, and (b) alignment-driven finetuning, which selectively updates either the policy or the model as needed using efficient low-rank updates. Extensive experiments on the challenging CARLA driving tasks demonstrate that AdaWM significantly improves the finetuning process, resulting in more robust and efficient performance in autonomous driving systems.

cs.RO↗

arXiv2024

MTA: Multimodal Task Alignment for BEV Perception and Captioning

Bird's eye view (BEV)-based 3D perception plays a crucial role in autonomous driving applications. The rise of large language models has spurred interest in BEV-based captioning to understand object behavior in the surrounding environment. However, existing approaches treat perception and captioning as separate tasks, focusing on the performance of only one task and overlooking the potential benefits of multimodal alignment. To bridge this gap between modalities, we introduce MTA, a novel multimodal task alignment framework that boosts both BEV perception and captioning. MTA consists of two key components: (1) BEV-Language Alignment (BLA), a contextual learning mechanism that aligns the BEV scene representations with ground-truth language representations, and (2) Detection-Captioning Alignment (DCA), a cross-modal prompting mechanism that aligns detection and captioning outputs. MTA seamlessly integrates into state-of-the-art baselines during training, adding no extra computational complexity at runtime. Extensive experiments on the nuScenes and TOD3Cap datasets show that MTA significantly outperforms state-of-the-art baselines in both tasks, achieving a 10.7% improvement in challenging rare perception scenarios and a 9.2% improvement in captioning. These results underscore the effectiveness of unified alignment in reconciling BEV-based perception and captioning.

cs.CV↗

arXiv2024

VideoCogQA: A Controllable Benchmark for Evaluating Cognitive Abilities in Video-Language Models

Recent advancements in Large Video-Language Models (LVLMs) have led to promising results in multimodal video understanding. However, it remains unclear whether these models possess the cognitive capabilities required for high-level tasks, particularly those involving symbolic and abstract perception. Existing benchmarks typically rely on real-world, annotated videos, which lack control over video content and inherent difficulty, limiting their diagnostic power. To bridge this gap, we propose VideoCogQA, a scalable and fully controllable benchmark inspired by game-world environments, designed to evaluate the cognitive abilities of LVLMs. By generating synthetic videos via a programmatic engine, VideoCogQA allows fine-grained control over visual elements, temporal dynamics, and task difficulty. This approach enables a focused evaluation of video cognitive abilities, independent of prior knowledge from visual scene semantics. The dataset includes 800 videos and 3,280 question-answer pairs, featuring tasks related to abstract concepts, symbolic elements, and multimodal integration, with varying levels of difficulty. Experimental results show that even state-of-the-art (SOTA) models, such as GPT-4o, achieve an average performance of 48.8% on tasks involving abstract concepts. Additionally, performance drops by 15% as task complexity increases, highlighting the challenges LVLMs face in maintaining consistent performance. Through this work, we hope to show the limitations of current LVLMs and offer insights into how they can more effectively emulate human cognitive processes in the future.

cs.CV↗

arXiv2024

Optimizing Instruction Synthesis: Effective Exploration of Evolutionary Space with Tree Search

Instruction tuning is a crucial technique for aligning language models with humans' actual goals in the real world. Extensive research has highlighted the quality of instruction data is essential for the success of this alignment. However, creating high-quality data manually is labor-intensive and time-consuming, which leads researchers to explore using LLMs to synthesize data. Recent studies have focused on using a stronger LLM to iteratively enhance existing instruction data, showing promising results. Nevertheless, previous work often lacks control over the evolution direction, resulting in high uncertainty in the data synthesis process and low-quality instructions. In this paper, we introduce a general and scalable framework, IDEA-MCTS (Instruction Data Enhancement using Monte Carlo Tree Search), a scalable framework for efficiently synthesizing instructions. With tree search and evaluation models, it can efficiently guide each instruction to evolve into a high-quality form, aiding in instruction fine-tuning. Experimental results show that IDEA-MCTS significantly enhances the seed instruction data, raising the average evaluation scores of quality, diversity, and complexity from 2.19 to 3.81. Furthermore, in open-domain benchmarks, experimental results show that IDEA-MCTS improves the accuracy of real-world instruction-following skills in LLMs by an average of 5\% in low-resource settings.

cs.AI↗

arXiv2024

LORD: Large Models based Opposite Reward Design for Autonomous Driving

Reinforcement learning (RL) based autonomous driving has emerged as a promising alternative to data-driven imitation learning approaches. However, crafting effective reward functions for RL poses challenges due to the complexity of defining and quantifying good driving behaviors across diverse scenarios. Recently, large pretrained models have gained significant attention as zero-shot reward models for tasks specified with desired linguistic goals. However, the desired linguistic goals for autonomous driving such as "drive safely" are ambiguous and incomprehensible by pretrained models. On the other hand, undesired linguistic goals like "collision" are more concrete and tractable. In this work, we introduce LORD, a novel large models based opposite reward design through undesired linguistic goals to enable the efficient use of large pretrained models as zero-shot reward models. Through extensive experiments, our proposed framework shows its efficiency in leveraging the power of large pretrained models for achieving safe and enhanced autonomous driving. Moreover, the proposed approach shows improved generalization capabilities as it outperforms counterpart methods across diverse and challenging driving scenarios.

cs.RO↗

arXiv2023

F2BEV: Bird's Eye View Generation from Surround-View Fisheye Camera Images for Automated Driving

Bird's Eye View (BEV) representations are tremendously useful for perception-related automated driving tasks. However, generating BEVs from surround-view fisheye camera images is challenging due to the strong distortions introduced by such wide-angle lenses. We take the first step in addressing this challenge and introduce a baseline, F2BEV, to generate discretized BEV height maps and BEV semantic segmentation maps from fisheye images. F2BEV consists of a distortion-aware spatial cross attention module for querying and consolidating spatial information from fisheye image features in a transformer-style architecture followed by a task-specific head. We evaluate single-task and multi-task variants of F2BEV on our synthetic FB-SSEM dataset, all of which generate better BEV height and segmentation maps (in terms of the IoU) than a state-of-the-art BEV generation method operating on undistorted fisheye images. We also demonstrate discretized height map generation from real-world fisheye images using F2BEV. Our dataset is publicly available at https://github.com/volvo-cars/FB-SSEM-dataset

cs.CV↗

arXiv2021

DG-Labeler and DGL-MOTS Dataset: Boost the Autonomous Driving Perception

Multi-object tracking and segmentation (MOTS) is a critical task for autonomous driving applications. The existing MOTS studies face two critical challenges: 1) the published datasets inadequately capture the real-world complexity for network training to address various driving settings; 2) the working pipeline annotation tool is under-studied in the literature to improve the quality of MOTS learning examples. In this work, we introduce the DG-Labeler and DGL-MOTS dataset to facilitate the training data annotation for the MOTS task and accordingly improve network training accuracy and efficiency. DG-Labeler uses the novel Depth-Granularity Module to depict the instance spatial relations and produce fine-grained instance masks. Annotated by DG-Labeler, our DGL-MOTS dataset exceeds the prior effort (i.e., KITTI MOTS and BDD100K) in data diversity, annotation quality, and temporal representations. Results on extensive cross-dataset evaluations indicate significant performance improvements for several state-of-the-art methods trained on our DGL-MOTS dataset. We believe our DGL-MOTS Dataset and DG-Labeler hold the valuable potential to boost the visual perception of future transportation.

cs.CV↗

arXiv2020

Human-guided Robot Behavior Learning: A GAN-assisted Preference-based Reinforcement Learning Approach

Human demonstrations can provide trustful samples to train reinforcement learning algorithms for robots to learn complex behaviors in real-world environments. However, obtaining sufficient demonstrations may be impractical because many behaviors are difficult for humans to demonstrate. A more practical approach is to replace human demonstrations by human queries, i.e., preference-based reinforcement learning. One key limitation of the existing algorithms is the need for a significant amount of human queries because a large number of labeled data is needed to train neural networks for the approximation of a continuous, high-dimensional reward function. To reduce and minimize the need for human queries, we propose a new GAN-assisted human preference-based reinforcement learning approach that uses a generative adversarial network (GAN) to actively learn human preferences and then replace the role of human in assigning preferences. The adversarial neural network is simple and only has a binary output, hence requiring much less human queries to train. Moreover, a maximum entropy based reinforcement learning algorithm is designed to shape the loss towards the desired regions or away from the undesired regions. To show the effectiveness of the proposed approach, we present some studies on complex robotic tasks without access to the environment reward in a typical MuJoCo robot locomotion environment. The obtained results show our method can achieve a reduction of about 99.8% human time without performance sacrifice.

cs.RO↗