Ziyan Wang

Xidong Feng, Yicheng Luo, Ziyan Wang et al. · cmu

When solving decision-making tasks, humans typically depend on information from two key sources: (1) Historical policy data, which provides interaction replay from the environment, and (2) Analytical insights in natural language form, exposing the invaluable thought process or strategic considerations. Despite this, the majority of preceding research focuses on only one source: they either use historical replay exclusively to directly learn policy or value functions, or engaged in language model training utilizing mere language corpus. In this paper, we argue that a powerful autonomous agent should cover both sources. Thus, we propose ChessGPT, a GPT model bridging policy learning and language modeling by integrating data from these two sources in Chess games. Specifically, we build a large-scale game and language dataset related to chess. Leveraging the dataset, we showcase two model examples ChessCLIP and ChessGPT, integrating policy learning and language modeling. Finally, we propose a full evaluation framework for evaluating language model's chess ability. Experimental results validate our model and dataset's effectiveness. We open source our code, model, and dataset at https://github.com/waterhorse1/ChessGPT.

Xiaoyuan Cheng, Haoyu Wang, Wenxuan Yuan et al. · cmu

Recent advances in flow-based offline reinforcement learning (RL) have achieved strong performance by parameterizing policies via flow matching. However, they still face critical trade-offs among expressiveness, optimality, and efficiency. In particular, existing flow policies interpret the $L_2$ regularization as an upper bound of the 2-Wasserstein distance ($W_2$), which can be problematic in offline settings. This issue stems from a fundamental geometric mismatch: the behavioral policy manifold is inherently anisotropic, whereas the $L_2$ (or upper bound of $W_2$) regularization is isotropic and density-insensitive, leading to systematically misaligned optimization directions. To address this, we revisit offline RL from a geometric perspective and show that policy refinement can be formulated as a local transport map: an initial flow policy augmented by a residual displacement. By analyzing the induced density transformation, we derive a local quadratic approximation of the KL-constrained objective governed by the Fisher information matrix, enabling a tractable anisotropic optimization formulation. By leveraging the score function embedded in the flow velocity, we obtain a corresponding quadratic constraint for efficient optimization. Our results reveal that the optimality gap in prior methods arises from their isotropic approximation. In contrast, our framework achieves a controllable approximation error within a provable neighborhood of the optimal solution. Extensive experiments demonstrate state-of-the-art performance across diverse offline RL benchmarks. See project page: https://github.com/ARC0127/Fisher-Decorator.

Ziyan Wang, Zhankun Xiong, Feng Huang et al.

Drug-drug interactions (DDIs) can result in various pharmacological changes, which can be categorized into different classes known as DDI events (DDIEs). In recent years, previously unobserved/unseen DDIEs have been emerging, posing a new classification task when unseen classes have no labelled instances in the training stage, which is formulated as a zero-shot DDIE prediction (ZS-DDIE) task. However, existing computational methods are not directly applicable to ZS-DDIE, which has two primary challenges: obtaining suitable DDIE representations and handling the class imbalance issue. To overcome these challenges, we propose a novel method named ZeroDDI for the ZS-DDIE task. Specifically, we design a biological semantic enhanced DDIE representation learning module, which emphasizes the key biological semantics and distills discriminative molecular substructure-related semantics for DDIE representation learning. Furthermore, we propose a dual-modal uniform alignment strategy to distribute drug pair representations and DDIE semantic representations uniformly in a unit sphere and align the matched ones, which can mitigate the issue of class imbalance. Extensive experiments showed that ZeroDDI surpasses the baselines and indicate that it is a promising tool for detecting unseen DDIEs. Our code has been released in https://github.com/wzy-Sarah/ZeroDDI.

Wanhao Yu, Ziyan Wang, Zheng Wang et al.

Zeroth-order (ZO) optimization enables memory-efficient fine-tuning of large language models (LLMs) using only forward passes, but it remains unclear how useful adaptation is distributed across layers. In this work, we reveal a surprising phenomenon: ZO fine-tuning is sharply dominated by a single decoding layer. Across multiple LLM families and downstream tasks, fine-tuning this dominant layer alone consistently matches or even exceeds full-model ZO fine-tuning. We further show that the dominant layer is task-agnostic but model-specific, and can be identified before training through a simple inference-only analysis of activation outliers. Specifically, the dominant layer consistently aligns with the first activation-outlier layer in the pre-trained model. To explain this phenomenon, we analyze how perturbation effects propagate under ZO optimization. We find that the dominant layer combines two key properties: high perturbation sensitivity and early placement in the residual stream, allowing perturbation-induced effects to propagate and accumulate through remaining subsequent decoding layers. As a result, this layer produces disproportionately strong and stable optimization signals under forward-only updates. Extensive experiments on LLaMA2-7B and Qwen3-8B across nine benchmarks show that dominant-layer ZO fine-tuning improves average performance over full-model MeZO and LoRA-based ZO fine-tuning while achieving up to 4.52$\times$ training speedup.

Abeer Matar A. Almalky, Ziyan Wang, Mohaiminul Al Nahian et al.

In recent years, large language models (LLMs) have achieved remarkable advances and are increasingly deployed in critical applications across diverse domains. This growing adoption raises urgent concerns about their security and robustness. In this work, we investigate the impact of Bit Flip Attacks (BFAs) on LLMs, which exploit hardware faults to corrupt model parameters, thereby threatening model integrity and performance. Existing BFA studies primarily assume a white-box setting with access to exact model weights and part of the dataset, and rely on progressive gradient-based bit-search strategies to identify vulnerable bits in model weights. However, gradient computation for LLMs is computationally expensive and memory intensive. In addition, assuming access to exact victim model weights and datasets is challenging due to increasingly strict user privacy regulations. To address these challenges, we propose the first gray-box BFA framework for LLMs, Invisible Hands, designed for efficient and practical deployment. Our method, Gradient-Data-Free-BFA, identifies vulnerable weight bits without requiring knowledge of model weights, gradients, or sample data. It introduces novel vulnerability index metrics that estimate the weights of susceptibility based solely on model architecture (Grey-Box). By eliminating data access and gradient computation, our approach significantly reduces memory overhead and scales efficiently across tasks with constant complexity. Experiments on six open-source LLMs demonstrate that adversarial objectives can be achieved with minimal weight perturbations, highlighting the effectiveness and practicality of Invisible Hands.

Radu Alexandru Rosu, Shunsuke Saito, Ziyan Wang et al.

We present Neural Strands, a novel learning framework for modeling accurate hair geometry and appearance from multi-view image inputs. The learned hair model can be rendered in real-time from any viewpoint with high-fidelity view-dependent effects. Our model achieves intuitive shape and style control unlike volumetric counterparts. To enable these properties, we propose a novel hair representation based on a neural scalp texture that encodes the geometry and appearance of individual strands at each texel location. Furthermore, we introduce a novel neural rendering framework based on rasterization of the learned hair strands. Our neural rendering is strand-accurate and anti-aliased, making the rendering view-consistent and photorealistic. Combining appearance with a multi-view geometric prior, we enable, for the first time, the joint learning of appearance and explicit hair geometry from a multi-view setup. We demonstrate the efficacy of our approach in terms of fidelity and efficiency for various hairstyles.

Vasilis Kontonis, Yuchen Zeng, Shivam Garg et al. · cmu

Reasoning models think in long, unstructured streams with no mechanism for compressing or organizing their own intermediate state. We introduce MEMENTO: a method that teaches models to segment reasoning into blocks, compress each block into a memento, i.e., a dense state summary, and reason forward by attending only to mementos, reducing context, KV cache, and compute. To train MEMENTO models, we release OpenMementos, a public dataset of 228K reasoning traces derived from OpenThoughts-v3, segmented and annotated with intermediate summaries. We show that a two-stage SFT recipe on OpenMementos is effective across different model families (Qwen3, Phi-4, Olmo 3) and scales (8B--32B parameters). Trained models maintain strong accuracy on math, science, and coding benchmarks while achieving ${\sim}2.5\times$ peak KV cache reduction. We extend vLLM to support our inference method, achieving ${\sim}1.75\times$ throughput improvement while also enabling us to perform RL and further improve accuracy. Finally, we identify a dual information stream: information from each reasoning block is carried both by the memento text and by the corresponding KV states, which retain implicit information from the original block. Removing this channel drops accuracy by 15\,pp on AIME24.

Ziyan Wang, Hao Wang

Existing regression models tend to fall short in both accuracy and uncertainty estimation when the label distribution is imbalanced. In this paper, we propose a probabilistic deep learning model, dubbed variational imbalanced regression (VIR), which not only performs well in imbalanced regression but naturally produces reasonable uncertainty estimation as a byproduct. Different from typical variational autoencoders assuming I.I.D. representations (a data point's representation is not directly affected by other data points), our VIR borrows data with similar regression labels to compute the latent representation's variational distribution; furthermore, different from deterministic regression models producing point estimates, VIR predicts the entire normal-inverse-gamma distributions and modulates the associated conjugate distributions to impose probabilistic reweighting on the imbalanced data, thereby providing better uncertainty estimation. Experiments in several real-world datasets show that our VIR can outperform state-of-the-art imbalanced regression models in terms of both accuracy and uncertainty estimation. Code will soon be available at https://github.com/Wang-ML-Lab/variational-imbalanced-regression.

Ziyan Wang, Giljoo Nam, Tuur Stuyck et al.

The capture and animation of human hair are two of the major challenges in the creation of realistic avatars for the virtual reality. Both problems are highly challenging, because hair has complex geometry and appearance, as well as exhibits challenging motion. In this paper, we present a two-stage approach that models hair independently from the head to address these challenges in a data-driven manner. The first stage, state compression, learns a low-dimensional latent space of 3D hair states containing motion and appearance, via a novel autoencoder-as-a-tracker strategy. To better disentangle the hair and head in appearance learning, we employ multi-view hair segmentation masks in combination with a differentiable volumetric renderer. The second stage learns a novel hair dynamics model that performs temporal hair transfer based on the discovered latent codes. To enforce higher stability while driving our dynamics model, we employ the 3D point-cloud autoencoder from the compression stage for de-noising of the hair state. Our model outperforms the state of the art in novel view synthesis and is capable of creating novel hair animations without having to rely on hair observations as a driving signal. Project page is here https://ziyanw1.github.io/neuwigs/.

Chandler Smith, Marwa Abdulhai, Manfred Diaz et al.

Large Language Model (LLM) agents have demonstrated impressive capabilities for social interaction and are increasingly being deployed in situations where they might engage with both human and artificial agents. These interactions represent a critical frontier for LLM-based agents, yet existing evaluation methods fail to measure how well these capabilities generalize to novel social situations. In this paper, we introduce a method for evaluating the ability of LLM-based agents to cooperate in zero-shot, mixed-motive environments using Concordia, a natural language multi-agent simulation environment. Our method measures general cooperative intelligence by testing an agent's ability to identify and exploit opportunities for mutual gain across diverse partners and contexts. We present empirical results from the NeurIPS 2024 Concordia Contest, where agents were evaluated on their ability to achieve mutual gains across a suite of diverse scenarios ranging from negotiation to collective action problems. Our findings reveal significant gaps between current agent capabilities and the robust generalization required for reliable cooperation, particularly in scenarios demanding persuasion and norm enforcement.

Ziyan Wang, Peng Chen, Ding Li et al. · cmu

Learning diverse and high-fidelity traffic simulations from human driving demonstrations is crucial for autonomous driving evaluation. The recent next-token prediction (NTP) paradigm, widely adopted in large language models (LLMs), has been applied to traffic simulation and achieves iterative improvements via supervised fine-tuning (SFT). However, such methods limit active exploration of potentially valuable motion tokens, particularly in suboptimal regions. Entropy patterns provide a promising perspective for enabling exploration driven by motion token uncertainty. Motivated by this insight, we propose a novel tokenized traffic simulation policy, R1Sim, which represents an initial attempt to explore reinforcement learning based on motion token entropy patterns, and systematically analyzes the impact of different motion tokens on simulation outcomes. Specifically, we introduce an entropy-guided adaptive sampling mechanism that focuses on previously overlooked motion tokens with high uncertainty yet high potential. We further optimize motion behaviors using Group Relative Policy Optimization (GRPO), guided by a safety-aware reward design. Overall, these components enable a balanced exploration-exploitation trade-off through diverse high-uncertainty sampling and group-wise comparative estimation, resulting in realistic, safe, and diverse multi-agent behaviors. Extensive experiments on the Waymo Sim Agent benchmark demonstrate that R1Sim achieves competitive performance compared to state-of-the-art methods.

Zeyu Xiong, Weitao Wang, Jing Yu et al.

In recent years, AI-generated music has made significant progress, with several models performing well in multimodal and complex musical genres and scenes. While objective metrics can be used to evaluate generative music, they often lack interpretability for musical evaluation. Therefore, researchers often resort to subjective user studies to assess the quality of the generated works, which can be resource-intensive and less reproducible than objective metrics. This study aims to comprehensively evaluate the subjective, objective, and combined methodologies for assessing AI-generated music, highlighting the advantages and disadvantages of each approach. Ultimately, this study provides a valuable reference for unifying generative AI in the field of music evaluation.

Ziyan Wang, Enmao Diao, Qi Le et al.

Reasoning LLMs (RLMs) such as OpenAI o1, DeepSeek-R1, and Qwen3 deliver strong multi-step reasoning through chain-of-thought generation, but their large model sizes and lengthy decode-time outputs make them costly to deploy and unsuitable for resource-constrained settings. To reduce computing and memory cost, pruning offers a promising solution by removing unimportant parameters. However, despite their success on standard LLMs, existing pruning methods severely damage RLMs, as even moderate sparsity (e.g., 20%) can collapse accuracy and completely disrupt the model's reasoning coherence. We begin by analyzing why existing pruning pipelines fail on reasoning LLMs and find that their brittleness largely stems from a mismatch between the calibration data, the pruning objective, and the model's decode-time reasoning behavior. Our study further shows that the most reliable calibration signal comes not from human-written labels but from the model's own self-generated reasoning traces, which more accurately reflect its inference distribution. Guided by these insights, we introduce RESP, a self-reflective structured pruning framework that aligns pruning decisions with the model's reasoning dynamics through self-generated calibration, decode-only gradient-based importance estimation, and progressive regeneration that maintains calibration fidelity as sparsity increases. Experiments on Qwen3-8B demonstrate that RESP markedly outperforms existing structured pruning methods on both GSM8K and MathQA, preserving near-dense accuracy at 20-30% sparsity and substantially mitigating performance collapse at higher sparsity levels. At 40% sparsity, RESP attains 81.3% accuracy on GSM8K and 59.6% on MathQA, surpassing the strongest baselines by 66.87% and 47%, respectively.

Junying Wang, Yuanlu Xu, Edith Tretschk et al.

The creation of photorealistic dynamic hair remains a major challenge in digital human modeling because of the complex motions, occlusions, and light scattering. Existing methods often resort to static capture and physics-based models that do not scale as they require manual parameter fine-tuning to handle the diversity of hairstyles and motions, and heavy computation to obtain high-quality appearance. In this paper, we present Dynamic Gaussian Hair (DGH), a novel framework that efficiently learns hair dynamics and appearance. We propose: (1) a coarse-to-fine model that learns temporally coherent hair motion dynamics across diverse hairstyles; (2) a strand-guided optimization module that learns a dynamic 3D Gaussian representation for hair appearance with support for differentiable rendering, enabling gradient-based learning of view-consistent appearance under motion. Unlike prior simulation-based pipelines, our approach is fully data-driven, scales with training data, and generalizes across various hairstyles and head motion sequences. Additionally, DGH can be seamlessly integrated into a 3D Gaussian avatar framework, enabling realistic, animatable hair for high-fidelity avatar representation. DGH achieves promising geometry and appearance results, providing a scalable, data-driven alternative to physics-based simulation and rendering.

Ziyan Wang, Yaxuan He, Bin Liu

Graph Neural Networks (GNNs) have achieved notable success in the analysis of non-Euclidean data across a wide range of domains. However, their applicability is constrained by the dependence on the observed graph structure. To solve this problem, Latent Graph Inference (LGI) is proposed to infer a task-specific latent structure by computing similarity or edge probability of node features and then apply a GNN to produce predictions. Even so, existing approaches neglect the noise from node features, which affects generated graph structure and performance. In this work, we introduce a novel method called Probability Passing to refine the generated graph structure by aggregating edge probabilities of neighboring nodes based on observed graph. Furthermore, we continue to utilize the LGI framework, inputting the refined graph structure and node features into GNNs to obtain predictions. We name the proposed scheme as Probability Passing-based Graph Neural Network (PPGNN). Moreover, the anchor-based technique is employed to reduce complexity and improve efficiency. Experimental results demonstrate the effectiveness of the proposed method.

Ziyan wang, Longlong Ma

In Chomsky's provocative critique "The False Promise of CHATGPT," Large Language Models (LLMs) are characterized as mere pattern predictors that do not acquire languages via intrinsic causal and self-correction structures like humans, therefore are not able to distinguish impossible languages. It stands as a representative in a fundamental challenge to the intellectual foundations of AI, for it integrally synthesizes major issues in methodologies within LLMs and possesses an iconic a priori rationalist perspective. We examine this famous critic from both the perspective in pre-existing literature of linguistics and psychology as well as a research based on an experiment inquiring the capacity of learning both possible and impossible languages among LLMs. We constructed a set of syntactically impossible languages by applying certain transformations to English. These include reversing whole sentences, and adding negation based on word-count parity. Two rounds of controlled experiments were each conducted on GPT-2 small models and long short-term memory (LSTM) models. Statistical analysis (Welch's t-test) shows GPT2 small models underperform in learning all of the impossible languages compared to their performance on the possible language (p<.001). On the other hand, LSTM models' performance tallies with Chomsky's argument, suggesting the irreplaceable role of the evolution of transformer architecture. Based on theoretical analysis and empirical findings, we propose a new vision within Chomsky's theory towards LLMs, and a shift of theoretical paradigm outside Chomsky, from his "rationalist-romantics" paradigm to functionalism and empiricism in LLMs research.

Ziyan Wang, Yingpeng Du, Zhu Sun et al.

Large Language Models (LLMs) are emerging as promising approaches to enhance session-based recommendation (SBR), where both prompt-based and fine-tuning-based methods have been widely investigated to align LLMs with SBR. However, the former methods struggle with optimal prompts to elicit the correct reasoning of LLMs due to the lack of task-specific feedback, leading to unsatisfactory recommendations. Although the latter methods attempt to fine-tune LLMs with domain-specific knowledge, they face limitations such as high computational costs and reliance on open-source backbones. To address such issues, we propose a Reflective Reinforcement Large Language Model (Re2LLM) for SBR, guiding LLMs to focus on specialized knowledge essential for more accurate recommendations effectively and efficiently. In particular, we first design the Reflective Exploration Module to effectively extract knowledge that is readily understandable and digestible by LLMs. To be specific, we direct LLMs to examine recommendation errors through self-reflection and construct a knowledge base (KB) comprising hints capable of rectifying these errors. To efficiently elicit the correct reasoning of LLMs, we further devise the Reinforcement Utilization Module to train a lightweight retrieval agent. It learns to select hints from the constructed KB based on the task-specific feedback, where the hints can serve as guidance to help correct LLMs reasoning for better recommendations. Extensive experiments on multiple real-world datasets demonstrate that our method consistently outperforms state-of-the-art methods.

Ziyan Wang, Bin Liu, Ling Xiang

Graph Neural Networks (GNNs) have recently achieved significant success, with a key operation involving the aggregation of information from neighboring nodes. Substantial researchers have focused on defining neighbors for aggregation, predominantly based on observed adjacency matrices. However, in many scenarios, the explicitly given graphs contain noise, which can be amplified during the messages-passing process. Therefore, many researchers have turned their attention to latent graph inference, specifically learning a parametric graph. To mitigate fluctuations in latent graph structure learning, this paper proposes a novel Boolean product-based graph residual connection in GNNs to link the latent graph and the original graph. It computes the Boolean product between the latent graph and the original graph at each layer to correct the learning process. The Boolean product between two adjacency matrices is equivalent to triangle detection. Accordingly, the proposed Boolean product graph neural networks can be interpreted as discovering triangular cliques from the original and the latent graph. We validate the proposed method in benchmark datasets and demonstrate its ability to enhance the performance and robustness of GNNs.

Qi Le, Enmao Diao, Ziyan Wang et al.

We introduce Probe Pruning (PP), a novel framework for online, dynamic, structured pruning of Large Language Models (LLMs) applied in a batch-wise manner. PP leverages the insight that not all samples and tokens contribute equally to the model's output, and probing a small portion of each batch effectively identifies crucial weights, enabling tailored dynamic pruning for different batches. It comprises three main stages: probing, history-informed pruning, and full inference. In the probing stage, PP selects a small yet crucial set of hidden states, based on residual importance, to run a few model layers ahead. During the history-informed pruning stage, PP strategically integrates the probing states with historical states. Subsequently, it structurally prunes weights based on the integrated states and the PP importance score, a metric developed specifically to assess the importance of each weight channel in maintaining performance. In the final stage, full inference is conducted on the remaining weights. A major advantage of PP is its compatibility with existing models, as it operates without requiring additional neural network modules or fine-tuning. Comprehensive evaluations of PP on LLaMA-2/3 and OPT models reveal that even minimal probing-using just 1.5% of FLOPs-can substantially enhance the efficiency of structured pruning of LLMs. For instance, when evaluated on LLaMA-2-7B with WikiText2, PP achieves a 2.56 times lower ratio of performance degradation per unit of runtime reduction compared to the state-of-the-art method at a 40% pruning ratio. Our code is available at https://github.com/Qi-Le1/Probe_Pruning.

Rong Wang, Fabian Prada, Ziyan Wang et al.

We present a novel method for reconstructing personalized 3D human avatars with realistic animation from only a few images. Due to the large variations in body shapes, poses, and cloth types, existing methods mostly require hours of per-subject optimization during inference, which limits their practical applications. In contrast, we learn a universal prior from over a thousand clothed humans to achieve instant feedforward generation and zero-shot generalization. Specifically, instead of rigging the avatar with shared skinning weights, we jointly infer personalized avatar shape, skinning weights, and pose-dependent deformations, which effectively improves overall geometric fidelity and reduces deformation artifacts. Moreover, to normalize pose variations and resolve coupled ambiguity between canonical shapes and skinning weights, we design a 3D canonicalization process to produce pixel-aligned initial conditions, which helps to reconstruct fine-grained geometric details. We then propose a multi-frame feature aggregation to robustly reduce artifacts introduced in canonicalization and fuse a plausible avatar preserving person-specific identities. Finally, we train the model in an end-to-end framework on a large-scale capture dataset, which contains diverse human subjects paired with high-quality 3D scans. Extensive experiments show that our method generates more authentic reconstruction and animation than state-of-the-arts, and can be directly generalized to inputs from casually taken phone photos. Project page and code is available at https://github.com/rongakowang/FRESA.

Zhicheng Zhang, Ziyan Wang, Yali Du et al.

Exploration remains a key bottleneck for reinforcement learning (RL) post-training of large language models (LLMs), where sparse feedback and large action spaces can lead to premature collapse into repetitive behaviors. We propose Verbalized Action Masking (VAM), which verbalizes an action mask in the prompt and enforces that the model outputs an action from the masked set. Building on this interface, we introduce iterative action-space pruning: if the target action is not sampled, we remove valid sampled actions from the mask and resample under the reduced candidate set, repeating until the target is sampled or a fixed budget is exhausted. We study VAM in chess and evaluate it under two training regimes: an engine-play regime that generates states via play against an engine opponent and a fixed-dataset regime that trains from a fixed dataset of positions with verifier scores. Across held-out chess puzzles and full-game play measured by average centipawn loss (ACPL), VAM improves learning efficiency and final performance over strong baselines, highlighting verbalized masking as a practical mechanism for controllable exploration in LLM RL post-training.

Marco Pesavento, Yuanlu Xu, Nikolaos Sarafianos et al.

Recent progress in human shape learning, shows that neural implicit models are effective in generating 3D human surfaces from limited number of views, and even from a single RGB image. However, existing monocular approaches still struggle to recover fine geometric details such as face, hands or cloth wrinkles. They are also easily prone to depth ambiguities that result in distorted geometries along the camera optical axis. In this paper, we explore the benefits of incorporating depth observations in the reconstruction process by introducing ANIM, a novel method that reconstructs arbitrary 3D human shapes from single-view RGB-D images with an unprecedented level of accuracy. Our model learns geometric details from both multi-resolution pixel-aligned and voxel-aligned features to leverage depth information and enable spatial relationships, mitigating depth ambiguities. We further enhance the quality of the reconstructed shape by introducing a depth-supervision strategy, which improves the accuracy of the signed distance field estimation of points that lie on the reconstructed surface. Experiments demonstrate that ANIM outperforms state-of-the-art works that use RGB, surface normals, point cloud or RGB-D data as input. In addition, we introduce ANIM-Real, a new multi-modal dataset comprising high-quality scans paired with consumer-grade RGB-D camera, and our protocol to fine-tune ANIM, enabling high-quality reconstruction from real-world human capture.

Lingdong Kong, Shaoyuan Xie, Hanjiang Hu et al. · tsinghua

In the realm of autonomous driving, robust perception under out-of-distribution conditions is paramount for the safe deployment of vehicles. Challenges such as adverse weather, sensor malfunctions, and environmental unpredictability can severely impact the performance of autonomous systems. The 2024 RoboDrive Challenge was crafted to propel the development of driving perception technologies that can withstand and adapt to these real-world variabilities. Focusing on four pivotal tasks -- BEV detection, map segmentation, semantic occupancy prediction, and multi-view depth estimation -- the competition laid down a gauntlet to innovate and enhance system resilience against typical and atypical disturbances. This year's challenge consisted of five distinct tracks and attracted 140 registered teams from 93 institutes across 11 countries, resulting in nearly one thousand submissions evaluated through our servers. The competition culminated in 15 top-performing solutions, which introduced a range of innovative approaches including advanced data augmentation, multi-sensor fusion, self-supervised learning for error correction, and new algorithmic strategies to enhance sensor robustness. These contributions significantly advanced the state of the art, particularly in handling sensor inconsistencies and environmental variability. Participants, through collaborative efforts, pushed the boundaries of current technologies, showcasing their potential in real-world scenarios. Extensive evaluations and analyses provided insights into the effectiveness of these solutions, highlighting key trends and successful strategies for improving the resilience of driving perception systems. This challenge has set a new benchmark in the field, providing a rich repository of techniques expected to guide future research in this field.

Yingpeng Du, Ziyan Wang, Zhu Sun et al.

In recent years, efforts have been made to use text information for better user profiling and item characterization in recommendations. However, text information can sometimes be of low quality, hindering its effectiveness for real-world applications. With knowledge and reasoning capabilities capsuled in Large Language Models (LLMs), utilizing LLMs emerges as a promising way for description improvement. However, existing ways of prompting LLMs with raw texts ignore structured knowledge of user-item interactions, which may lead to hallucination problems like inconsistent description generation. To this end, we propose a Graph-aware Convolutional LLM method to elicit LLMs to capture high-order relations in the user-item graph. To adapt text-based LLMs with structured graphs, We use the LLM as an aggregator in graph processing, allowing it to understand graph-based information step by step. Specifically, the LLM is required for description enhancement by exploring multi-hop neighbors layer by layer, thereby propagating information progressively in the graph. To enable LLMs to capture large-scale graph information, we break down the description task into smaller parts, which drastically reduces the context length of the token input with each step. Extensive experiments on three real-world datasets show that our method consistently outperforms state-of-the-art methods.

Xidong Feng, Ziyu Wan, Mengyue Yang et al. · cmu

Reinforcement Learning (RL) has shown remarkable abilities in learning policies for decision-making tasks. However, RL is often hindered by issues such as low sample efficiency, lack of interpretability, and sparse supervision signals. To tackle these limitations, we take inspiration from the human learning process and introduce Natural Language Reinforcement Learning (NLRL), which innovatively combines RL principles with natural language representation. Specifically, NLRL redefines RL concepts like task objectives, policy, value function, Bellman equation, and policy iteration in natural language space. We present how NLRL can be practically implemented with the latest advancements in large language models (LLMs) like GPT-4. Initial experiments over tabular MDPs demonstrate the effectiveness, efficiency, and also interpretability of the NLRL framework.

Ziyan Wang, Zhicheng Zhang, Fei Fang et al. · cmu

Designing effective reward functions in multi-agent reinforcement learning (MARL) is a significant challenge, often leading to suboptimal or misaligned behaviors in complex, coordinated environments. We introduce Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality ($\text{M}^3\text{HF}$), a novel framework that integrates multi-phase human feedback of mixed quality into the MARL training process. By involving humans with diverse expertise levels to provide iterative guidance, $\text{M}^3\text{HF}$ leverages both expert and non-expert feedback to continuously refine agents' policies. During training, we strategically pause agent learning for human evaluation, parse feedback using large language models to assign it appropriately and update reward functions through predefined templates and adaptive weights by using weight decay and performance-based adjustments. Our approach enables the integration of nuanced human insights across various levels of quality, enhancing the interpretability and robustness of multi-agent cooperation. Empirical results in challenging environments demonstrate that $\text{M}^3\text{HF}$ significantly outperforms state-of-the-art methods, effectively addressing the complexities of reward design in MARL and enabling broader human participation in the training process.

Ziyan Wang, Yali Du, Yudi Zhang et al. · cmu

Offline Multi-agent Reinforcement Learning (MARL) is valuable in scenarios where online interaction is impractical or risky. While independent learning in MARL offers flexibility and scalability, accurately assigning credit to individual agents in offline settings poses challenges because interactions with an environment are prohibited. In this paper, we propose a new framework, namely Multi-Agent Causal Credit Assignment (MACCA), to address credit assignment in the offline MARL setting. Our approach, MACCA, characterizing the generative process as a Dynamic Bayesian Network, captures relationships between environmental variables, states, actions, and rewards. Estimating this model on offline data, MACCA can learn each agent's contribution by analyzing the causal relationship of their individual rewards, ensuring accurate and interpretable credit assignment. Additionally, the modularity of our approach allows it to seamlessly integrate with various offline MARL methods. Theoretically, we proved that under the setting of the offline dataset, the underlying causal structure and the function for generating the individual rewards of agents are identifiable, which laid the foundation for the correctness of our modeling. In our experiments, we demonstrate that MACCA not only outperforms state-of-the-art methods but also enhances performance when integrated with other backbones.

Yingpeng Du, Zhu Sun, Ziyan Wang et al.

Large language models (LLMs) provide a promising way for accurate session-based recommendation (SBR), but they demand substantial computational time and memory. Knowledge distillation (KD)-based methods can alleviate these issues by transferring the knowledge to a small student, which trains a student based on the predictions of a cumbersome teacher. However, these methods encounter difficulties for \textit{LLM-based KD in SBR}. 1) It is expensive to make LLMs predict for all instances in KD. 2) LLMs may make ineffective predictions for some instances in KD, e.g., incorrect predictions for hard instances or similar predictions as existing recommenders for easy instances. In this paper, we propose an active LLM-based KD method in SBR, contributing to sustainable AI. To efficiently distill knowledge from LLMs with limited cost, we propose to extract a small proportion of instances predicted by LLMs. Meanwhile, for a more effective distillation, we propose an active learning strategy to extract instances that are as effective as possible for KD from a theoretical view. Specifically, we first formulate gains based on potential effects (e.g., effective, similar, and incorrect predictions by LLMs) and difficulties (e.g., easy or hard to fit) of instances for KD. Then, we propose to maximize the minimal gains of distillation to find the optimal selection policy for active learning, which can largely avoid extracting ineffective instances in KD. Experiments on real-world datasets show that our method significantly outperforms state-of-the-art methods for SBR.

Xingzhou Lou, Junge Zhang, Ziyan Wang et al. · cmu

Safe reinforcement learning (RL) agents accomplish given tasks while adhering to specific constraints. Employing constraints expressed via easily-understandable human language offers considerable potential for real-world applications due to its accessibility and non-reliance on domain expertise. Previous safe RL methods with natural language constraints typically adopt a recurrent neural network, which leads to limited capabilities when dealing with various forms of human language input. Furthermore, these methods often require a ground-truth cost function, necessitating domain expertise for the conversion of language constraints into a well-defined cost function that determines constraint violation. To address these issues, we proposes to use pre-trained language models (LM) to facilitate RL agents' comprehension of natural language constraints and allow them to infer costs for safe policy learning. Through the use of pre-trained LMs and the elimination of the need for a ground-truth cost, our method enhances safe policy learning under a diverse set of human-derived free-form natural language constraints. Experiments on grid-world navigation and robot control show that the proposed method can achieve strong performance while adhering to given constraints. The usage of pre-trained LMs allows our method to comprehend complicated constraints and learn safe policies without the need for ground-truth cost at any stage of training or evaluation. Extensive ablation studies are conducted to demonstrate the efficacy of each part of our method.

Ziyan Wang, Giljoo Nam, Aljaz Bozic et al.

Hair plays a significant role in personal identity and appearance, making it an essential component of high-quality, photorealistic avatars. Existing approaches either focus on modeling the facial region only or rely on personalized models, limiting their generalizability and scalability. In this paper, we present a novel method for creating high-fidelity avatars with diverse hairstyles. Our method leverages the local similarity across different hairstyles and learns a universal hair appearance prior from multi-view captures of hundreds of people. This prior model takes 3D-aligned features as input and generates dense radiance fields conditioned on a sparse point cloud with color. As our model splits different hairstyles into local primitives and builds prior at that level, it is capable of handling various hair topologies. Through experiments, we demonstrate that our model captures a diverse range of hairstyles and generalizes well to challenging new hairstyles. Empirical results show that our method improves the state-of-the-art approaches in capturing and generating photorealistic, personalized avatars with complete hair.

Ziyan Wang, Sizhe Wei, Xiaoming Huo et al. · gatech

Diffusion models have made significant advancements in recent years. However, their performance often deteriorates when trained or fine-tuned on imbalanced datasets. This degradation is largely due to the disproportionate representation of majority and minority data in image-text pairs. In this paper, we propose a general fine-tuning approach, dubbed PoGDiff, to address this challenge. Rather than directly minimizing the KL divergence between the predicted and ground-truth distributions, PoGDiff replaces the ground-truth distribution with a Product of Gaussians (PoG), which is constructed by combining the original ground-truth targets with the predicted distribution conditioned on a neighboring text embedding. Experiments on real-world datasets demonstrate that our method effectively addresses the imbalance problem in diffusion models, improving both generation accuracy and quality.

Ziyan Wang, Enmao Diao, Qi Le et al.

Structured pruning is a practical approach to deploying large language models (LLMs) efficiently, as it yields compact, hardware-friendly architectures. However, the dominant local paradigm is task-agnostic: by optimizing layer-wise reconstruction rather than task objectives, it tends to preserve perplexity or generic zero-shot behavior but fails to capitalize on modest task-specific calibration signals, often yielding limited downstream gains. We revisit global structured pruning and present GISP-Global Iterative Structured Pruning-a post-training method that removes attention heads and MLP channels using first-order, loss-based important weights aggregated at the structure level with block-wise normalization. An iterative schedule, rather than one-shot pruning, stabilizes accuracy at higher sparsity and mitigates perplexity collapse without requiring intermediate fine-tuning; the pruning trajectory also forms nested subnetworks that support a "prune-once, deploy-many" workflow. Furthermore, because importance is defined by a model-level loss, GISP naturally supports task-specific objectives; we instantiate perplexity for language modeling and a margin-based objective for decision-style tasks. Extensive experiments show that across Llama2-7B/13B, Llama3-8B, and Mistral-0.3-7B, GISP consistently lowers WikiText-2 perplexity and improves downstream accuracy, with especially strong gains at 40-50% sparsity; on DeepSeek-R1-Distill-Llama-3-8B with GSM8K, task-aligned calibration substantially boosts exact-match accuracy.

Ziyan Wang, Zheng Wang, Jie Fu et al.

Reinforcement learning (RL) has become central to enhancing reasoning in large language models (LLMs). Yet on-policy algorithms such as Group Relative Policy Optimization (GRPO) often suffer in early training: noisy gradients from low-quality rollouts lead to unstable updates and inefficient exploration. We introduce Slow-Fast Policy Optimization (SFPO), a simple yet efficient framework to address these limitations via decomposing each step into three stages: a short fast trajectory of inner steps on the same batch, a reposition mechanism to control off-policy drift, and a final slow correction. This reposition-before-update design preserves the objective and rollout process unchanged, making SFPO plug-compatible with existing policy-gradient pipelines. Extensive experiments demonstrate that SFPO consistently improves stability, reduces rollouts, and accelerates convergence of reasoning RL training. Specifically, it outperforms GRPO by up to 2.80 points in average on math reasoning benchmarks. It also achieves up to 4.93\texttimes{} fewer rollouts and an up to 4.19\texttimes{} reduction in wall-clock time to match GRPO's best accuracy.

Zhicheng Zhang, Ziyan Wang, Yali Du et al. · cmu

Developing effective instruction-following policies in reinforcement learning remains challenging due to the reliance on extensive human-labeled instruction datasets and the difficulty of learning from sparse rewards. In this paper, we propose a novel approach that leverages the capabilities of large language models (LLMs) to automatically generate open-ended instructions retrospectively from previously collected agent trajectories. Our core idea is to employ LLMs to relabel unsuccessful trajectories by identifying meaningful subtasks the agent has implicitly accomplished, thereby enriching the agent's training data and substantially alleviating reliance on human annotations. Through this open-ended instruction relabeling, we efficiently learn a unified instruction-following policy capable of handling diverse tasks within a single policy. We empirically evaluate our proposed method in the challenging Craftax environment, demonstrating clear improvements in sample efficiency, instruction coverage, and overall policy performance compared to state-of-the-art baselines. Our results highlight the effectiveness of utilizing LLM-guided open-ended instruction relabeling to enhance instruction-following reinforcement learning.

Jiawen Wang, Pei Cai, Ziyan Wang et al.

Purpose: This study aims to propose and investigate the feasibility of using Kolmogorov-Arnold Network (KAN) for CEST MRI data analysis (CEST-KAN). Methods: CEST MRI data were acquired from twelve healthy volunteers at 3T. Data from ten subjects were used for training, while the remaining two were reserved for testing. The performance of multi-layer perceptron (MLP) and KAN models with the same network settings were evaluated and compared to the conventional multi-pool Lorentzian fitting (MPLF) method in generating water and multiple CEST contrasts, including amide, relayed nuclear Overhauser effect (rNOE), and magnetization transfer (MT). Results: The water and CEST maps generated by both MLP and KAN were visually comparable to the MPLF results. However, the KAN model demonstrated higher accuracy in extrapolating the CEST fitting metrics, as evidenced by the smaller validation loss during training and smaller absolute error during testing. Voxel-wise correlation analysis showed that all four CEST fitting metrics generated by KAN consistently exhibited higher Pearson coefficients than the MLP results, indicating superior performance. Moreover, the KAN models consistently outperformed the MLP models in varying hidden layer numbers despite longer training time. Conclusion: In this study, we demonstrated for the first time the feasibility of utilizing KAN for CEST MRI data analysis, highlighting its superiority over MLP in this task. The findings suggest that CEST-KAN has the potential to be a robust and reliable post-analysis tool for CEST MRI in clinical settings.

Ziyan Wang, Xiaoming Huo, Hao Wang

Contextual bandit algorithms are essential for solving real-world decision making problems. In practice, collecting a contextual bandit's feedback from different domains may involve different costs. For example, measuring drug reaction from mice (as a source domain) and humans (as a target domain). Unfortunately, adapting a contextual bandit algorithm from a source domain to a target domain with distribution shift still remains a major challenge and largely unexplored. In this paper, we introduce the first general domain adaptation method for contextual bandits. Our approach learns a bandit model for the target domain by collecting feedback from the source domain. Our theoretical analysis shows that our algorithm maintains a sub-linear regret bound even adapting across domains. Empirical results show that our approach outperforms the state-of-the-art contextual bandit algorithms on real-world datasets.

Yudi Zhang, Yali Du, Biwei Huang et al.

A major challenge in reinforcement learning is to determine which state-action pairs are responsible for future rewards that are delayed. Reward redistribution serves as a solution to re-assign credits for each time step from observed sequences. While the majority of current approaches construct the reward redistribution in an uninterpretable manner, we propose to explicitly model the contributions of state and action from a causal perspective, resulting in an interpretable reward redistribution and preserving policy invariance. In this paper, we start by studying the role of causal generative models in reward redistribution by characterizing the generation of Markovian rewards and trajectory-wise long-term return and further propose a framework, called Generative Return Decomposition (GRD), for policy optimization in delayed reward scenarios. Specifically, GRD first identifies the unobservable Markovian rewards and causal relations in the generative process. Then, GRD makes use of the identified causal generative model to form a compact representation to train policy over the most favorable subspace of the state space of the agent. Theoretically, we show that the unobservable Markovian reward function is identifiable, as well as the underlying causal structure and causal models. Experimental results show that our method outperforms state-of-the-art methods and the provided visualization further demonstrates the interpretability of our method. The project page is located at https://reedzyd.github.io/GenerativeReturnDecomposition/.

Aivar Sootla, Alexander I. Cowen-Rivers, Taher Jafferjee et al.

Satisfying safety constraints almost surely (or with probability one) can be critical for the deployment of Reinforcement Learning (RL) in real-life applications. For example, plane landing and take-off should ideally occur with probability one. We address the problem by introducing Safety Augmented (Saute) Markov Decision Processes (MDPs), where the safety constraints are eliminated by augmenting them into the state-space and reshaping the objective. We show that Saute MDP satisfies the Bellman equation and moves us closer to solving Safe RL with constraints satisfied almost surely. We argue that Saute MDP allows viewing the Safe RL problem from a different perspective enabling new features. For instance, our approach has a plug-and-play nature, i.e., any RL algorithm can be "Sauteed". Additionally, state augmentation allows for policy generalization across safety constraints. We finally show that Saute RL algorithms can outperform their state-of-the-art counterparts when constraint satisfaction is of high importance.

Ziyan Wang, Giljoo Nam, Tuur Stuyck et al.

Capturing and rendering life-like hair is particularly challenging due to its fine geometric structure, the complex physical interaction and its non-trivial visual appearance.Yet, hair is a critical component for believable avatars. In this paper, we address the aforementioned problems: 1) we use a novel, volumetric hair representation that is com-posed of thousands of primitives. Each primitive can be rendered efficiently, yet realistically, by building on the latest advances in neural rendering. 2) To have a reliable control signal, we present a novel way of tracking hair on the strand level. To keep the computational effort manageable, we use guide hairs and classic techniques to expand those into a dense hood of hair. 3) To better enforce temporal consistency and generalization ability of our model, we further optimize the 3D scene flow of our representation with multi-view optical flow, using volumetric ray marching. Our method can not only create realistic renders of recorded multi-view sequences, but also create renderings for new hair configurations by providing new control signals. We compare our method with existing work on viewpoint synthesis and drivable animation and achieve state-of-the-art results. Please check out our project website at https://ziyanw1.github.io/hvh/.

David Mguni, Usman Islam, Yaqi Sun et al.

Reinforcement learning (RL) involves performing exploratory actions in an unknown system. This can place a learning agent in dangerous and potentially catastrophic system states. Current approaches for tackling safe learning in RL simultaneously trade-off safe exploration and task fulfillment. In this paper, we introduce a new generation of RL solvers that learn to minimise safety violations while maximising the task reward to the extent that can be tolerated by the safe policy. Our approach introduces a novel two-player framework for safe RL called Distributive Exploration Safety Training Algorithm (DESTA). The core of DESTA is a game between two adaptive agents: Safety Agent that is delegated the task of minimising safety violations and Task Agent whose goal is to maximise the environment reward. Specifically, Safety Agent can selectively take control of the system at any given point to prevent safety violations while Task Agent is free to execute its policy at any other states. This framework enables Safety Agent to learn to take actions at certain states that minimise future safety violations, both during training and testing time, while Task Agent performs actions that maximise the task performance everywhere else. Theoretically, we prove that DESTA converges to stable points enabling safety violations of pretrained policies to be minimised. Empirically, we show DESTA's ability to augment the safety of existing policies and secondly, construct safe RL policies when the Task Agent and Safety Agent are trained concurrently. We demonstrate DESTA's superior performance against leading RL methods in Lunar Lander and Frozen Lake from OpenAI gym.

Shangding Gu, Jakub Grudzien Kuba, Munning Wen et al.

Developing reinforcement learning algorithms that satisfy safety constraints is becoming increasingly important in real-world applications. In multi-agent reinforcement learning (MARL) settings, policy optimisation with safety awareness is particularly challenging because each individual agent has to not only meet its own safety constraints, but also consider those of others so that their joint behaviour can be guaranteed safe. Despite its importance, the problem of safe multi-agent learning has not been rigorously studied; very few solutions have been proposed, nor a sharable testing environment or benchmarks. To fill these gaps, in this work, we formulate the safe MARL problem as a constrained Markov game and solve it with policy optimisation methods. Our solutions -- Multi-Agent Constrained Policy Optimisation (MACPO) and MAPPO-Lagrangian -- leverage the theories from both constrained policy optimisation and multi-agent trust region learning. Crucially, our methods enjoy theoretical guarantees of both monotonic improvement in reward and satisfaction of safety constraints at every iteration. To examine the effectiveness of our methods, we develop the benchmark suite of Safe Multi-Agent MuJoCo that involves a variety of MARL baselines. Experimental results justify that MACPO/MAPPO-Lagrangian can consistently satisfy safety constraints, meanwhile achieving comparable performance to strong baselines.

Ziyan Wang, Timur Bagautdinov, Stephen Lombardi et al.

Photorealistic rendering of dynamic humans is an important ability for telepresence systems, virtual shopping, synthetic data generation, and more. Recently, neural rendering methods, which combine techniques from computer graphics and machine learning, have created high-fidelity models of humans and objects. Some of these methods do not produce results with high-enough fidelity for driveable human models (Neural Volumes) whereas others have extremely long rendering times (NeRF). We propose a novel compositional 3D representation that combines the best of previous methods to produce both higher-resolution and faster results. Our representation bridges the gap between discrete and continuous volumetric representations by combining a coarse 3D-structure-aware grid of animation codes with a continuous learned scene function that maps every position and its corresponding local animation code to its view-dependent emitted radiance and local volume density. Differentiable volume rendering is employed to compute photo-realistic novel views of the human head and upper body as well as to train our novel representation end-to-end using only 2D supervision. In addition, we show that the learned dynamic radiance field can be used to synthesize novel unseen expressions based on a global animation code. Our approach achieves state-of-the-art results for synthesizing novel views of dynamic human heads and the upper body.

Ziyan Wang, Buyu Liu, Samuel Schulter et al.

In this paper, we address the problem of inferring the layout of complex road scenes given a single camera as input. To achieve that, we first propose a novel parameterized model of road layouts in a top-view representation, which is not only intuitive for human visualization but also provides an interpretable interface for higher-level decision making. Moreover, the design of our top-view scene model allows for efficient sampling and thus generation of large-scale simulated data, which we leverage to train a deep neural network to infer our scene model's parameters. Specifically, our proposed training procedure uses supervised domain-adaptation techniques to incorporate both simulated as well as manually annotated data. Finally, we design a Conditional Random Field (CRF) that enforces coherent predictions for a single frame and encourages temporal smoothness among video frames. Experiments on two public data sets show that: (1) Our parametric top-view model is representative enough to describe complex road scenes; (2) The proposed method outperforms baselines trained on manually-annotated or simulated data only, thus getting the best of both; (3) Our CRF is able to generate temporally smoothed while semantically meaningful results.

Ricson Cheng, Ziyan Wang, Katerina Fragkiadaki

We present recurrent geometry-aware neural networks that integrate visual information across multiple views of a scene into 3D latent feature tensors, while maintaining an one-to-one mapping between 3D physical locations in the world scene and latent feature locations. Object detection, object segmentation, and 3D reconstruction is then carried out directly using the constructed 3D feature memory, as opposed to any of the input 2D images. The proposed models are equipped with differentiable egomotion-aware feature warping and (learned) depth-aware unprojection operations to achieve geometrically consistent mapping between the features in the input frame and the constructed latent model of the scene. We empirically show the proposed model generalizes much better than geometryunaware LSTM/GRU networks, especially under the presence of multiple objects and cross-object occlusions. Combined with active view selection policies, our model learns to select informative viewpoints to integrate information from by "undoing" cross-object occlusions, seamlessly combining geometry with learning from experience.

Rui Zhu, Chaoyang Wang, Chen-Hsuan Lin et al.

The problem of obtaining dense reconstruction of an object in a natural sequence of images has been long studied in computer vision. Classically this problem has been solved through the application of bundle adjustment (BA). More recently, excellent results have been attained through the application of photometric bundle adjustment (PBA) methods -- which directly minimize the photometric error across frames. A fundamental drawback to BA & PBA, however, is: (i) their reliance on having to view all points on the object, and (ii) for the object surface to be well textured. To circumvent these limitations we propose semantic PBA which incorporates a 3D object prior, obtained through deep learning, within the photometric bundle adjustment problem. We demonstrate state of the art performance in comparison to leading methods for object reconstruction across numerous natural sequences.

Rui Zhu, Chaoyang Wang, Chen-Hsuan Lin et al.

Reconstructing 3D shapes from a sequence of images has long been a problem of interest in computer vision. Classical Structure from Motion (SfM) methods have attempted to solve this problem through projected point displacement \& bundle adjustment. More recently, deep methods have attempted to solve this problem by directly learning a relationship between geometry and appearance. There is, however, a significant gap between these two strategies. SfM tackles the problem from purely a geometric perspective, taking no account of the object shape prior. Modern deep methods more often throw away geometric constraints altogether, rendering the results unreliable. In this paper we make an effort to bring these two seemingly disparate strategies together. We introduce learned shape prior in the form of deep shape generators into Photometric Bundle Adjustment (PBA) and propose to accommodate full 3D shape generated by the shape prior within the optimization-based inference framework, demonstrating impressive results.

Xinlei Pan, Yurong You, Ziyan Wang et al.

Reinforcement learning is considered as a promising direction for driving policy learning. However, training autonomous driving vehicle with reinforcement learning in real environment involves non-affordable trial-and-error. It is more desirable to first train in a virtual environment and then transfer to the real environment. In this paper, we propose a novel realistic translation network to make model trained in virtual environment be workable in real world. The proposed network can convert non-realistic virtual image input into a realistic one with similar scene structure. Given realistic frames as input, driving policy trained by reinforcement learning can nicely adapt to real world driving. Experiments show that our proposed virtual to real (VR) reinforcement learning (RL) works pretty well. To our knowledge, this is the first successful case of driving policy trained by reinforcement learning that can adapt to real world driving data.

Ziyan Wang, Jiwen Lu, Ruogu Lin et al.

In this paper, we propose a new correlated and individual multi-modal deep learning (CIMDL) method for RGB-D object recognition. Unlike most conventional RGB-D object recognition methods which extract features from the RGB and depth channels individually, our CIMDL jointly learns feature representations from raw RGB-D data with a pair of deep neural networks, so that the sharable and modal-specific information can be simultaneously exploited. Specifically, we construct a pair of deep convolutional neural networks (CNNs) for the RGB and depth data, and concatenate them at the top layer of the network with a loss function which learns a new feature space where both correlated part and the individual part of the RGB-D information are well modelled. The parameters of the whole networks are updated by using the back-propagation criterion. Experimental results on two widely used RGB-D object image benchmark datasets clearly show that our method outperforms state-of-the-arts.