Yi Shen

Zifan Wang, Yi Shen, Zachary I. Bell et al.

We consider risk-averse learning in repeated unknown games where the goal of the agents is to minimize their individual risk of incurring significantly high cost. Specifically, the agents use the conditional value at risk (CVaR) as a risk measure and rely on bandit feedback in the form of the cost values of the selected actions at every episode to estimate their CVaR values and update their actions. A major challenge in using bandit feedback to estimate CVaR is that the agents can only access their own cost values, which, however, depend on the actions of all agents. To address this challenge, we propose a new risk-averse learning algorithm with momentum that utilizes the full historical information on the cost values. We show that this algorithm achieves sub-linear regret and matches the best known algorithms in the literature. We provide numerical experiments for a Cournot game that show that our method outperforms existing methods.

Tencent Hunyuan Team, Ao Liu, Botong Zhou et al. · tencent-ai

As Large Language Models (LLMs) rapidly advance, we introduce Hunyuan-TurboS, a novel large hybrid Transformer-Mamba Mixture of Experts (MoE) model. It synergistically combines Mamba's long-sequence processing efficiency with Transformer's superior contextual understanding. Hunyuan-TurboS features an adaptive long-short chain-of-thought (CoT) mechanism, dynamically switching between rapid responses for simple queries and deep "thinking" modes for complex problems, optimizing computational resources. Architecturally, this 56B activated (560B total) parameter model employs 128 layers (Mamba2, Attention, FFN) with an innovative AMF/MF block pattern. Faster Mamba2 ensures linear complexity, Grouped-Query Attention minimizes KV cache, and FFNs use an MoE structure. Pre-trained on 16T high-quality tokens, it supports a 256K context length and is the first industry-deployed large-scale Mamba model. Our comprehensive post-training strategy enhances capabilities via Supervised Fine-Tuning (3M instructions), a novel Adaptive Long-short CoT Fusion method, Multi-round Deliberation Learning for iterative improvement, and a two-stage Large-scale Reinforcement Learning process targeting STEM and general instruction-following. Evaluations show strong performance: overall top 7 rank on LMSYS Chatbot Arena with a score of 1356, outperforming leading models like Gemini-2.0-Flash-001 (1352) and o4-mini-2025-04-16 (1345). TurboS also achieves an average of 77.9% across 23 automated benchmarks. Hunyuan-TurboS balances high performance and efficiency, offering substantial capabilities at lower inference costs than many reasoning models, establishing a new paradigm for efficient large-scale pre-trained models.

Xianfu Chen, Celimuge Wu, Yi Shen et al.

This article investigates a control system within the context of six-generation wireless networks. The control performance optimization confronts the technical challenges that arise from the intricate interactions between communication and control sub-systems, asking for a co-design. Accounting for the system dynamics, we formulate the sequential co-design decision-makings of communication and control over the discrete time horizon as a Markov decision process, for which a practical offline learning framework is proposed. Our proposed framework integrates large language models into the elements of reinforcement learning. We present a case study on the age of semantics-aware communication and control co-design to showcase the potentials from our proposed learning framework. Furthermore, we discuss the open issues remaining to make our proposed offline learning framework feasible for real-world implementations, and highlight the research directions for future explorations.

Zifan Wang, Yi Shen, Michael M. Zavlanos

We consider an online stochastic game with risk-averse agents whose goal is to learn optimal decisions that minimize the risk of incurring significantly high costs. Specifically, we use the Conditional Value at Risk (CVaR) as a risk measure that the agents can estimate using bandit feedback in the form of the cost values of only their selected actions. Since the distributions of the cost functions depend on the actions of all agents that are generally unobservable, they are themselves unknown and, therefore, the CVaR values of the costs are difficult to compute. To address this challenge, we propose a new online risk-averse learning algorithm that relies on one-point zeroth-order estimation of the CVaR gradients computed using CVaR values that are estimated by appropriately sampling the cost functions. We show that this algorithm achieves sub-linear regret with high probability. We also propose two variants of this algorithm that improve performance. The first variant relies on a new sampling strategy that uses samples from the previous iteration to improve the estimation accuracy of the CVaR values. The second variant employs residual feedback that uses CVaR values from the previous iteration to reduce the variance of the CVaR gradient estimates. We theoretically analyze the convergence properties of these variants and illustrate their performance on an online market problem that we model as a Cournot game.

Yi Shen, Pan Xu, Michael M. Zavlanos

Off-policy evaluation and learning are concerned with assessing a given policy and learning an optimal policy from offline data without direct interaction with the environment. Often, the environment in which the data are collected differs from the environment in which the learned policy is applied. To account for the effect of different environments during learning and execution, distributionally robust optimization (DRO) methods have been developed that compute worst-case bounds on the policy values assuming that the distribution of the new environment lies within an uncertainty set. Typically, this uncertainty set is defined based on the KL divergence around the empirical distribution computed from the logging dataset. However, the KL uncertainty set fails to encompass distributions with varying support and lacks awareness of the geometry of the distribution support. As a result, KL approaches fall short in addressing practical environment mismatches and lead to over-fitting to worst-case scenarios. To overcome these limitations, we propose a novel DRO approach that employs the Wasserstein distance instead. While Wasserstein DRO is generally computationally more expensive compared to KL DRO, we present a regularized method and a practical (biased) stochastic gradient descent method to optimize the policy efficiently. We also provide a theoretical analysis of the finite sample complexity and iteration complexity for our proposed method. We further validate our approach using a public dataset that was recorded in a randomized stoke trial.

Yi Shen, Jessilyn Dunn, Michael M. Zavlanos

In this paper, we consider a risk-averse multi-armed bandit (MAB) problem where the goal is to learn a policy that minimizes the risk of low expected return, as opposed to maximizing the expected return itself, which is the objective in the usual approach to risk-neutral MAB. Specifically, we formulate this problem as a transfer learning problem between an expert and a learner agent in the presence of contexts that are only observable by the expert but not by the learner. Thus, such contexts are unobserved confounders (UCs) from the learner's perspective. Given a dataset generated by the expert that excludes the UCs, the goal for the learner is to identify the true minimum-risk arm with fewer online learning steps, while avoiding possible biased decisions due to the presence of UCs in the expert's data.

Yi Shen, Jian Zhang, Jieyun Huang et al.

Recent advancements in slow thinking reasoning models have shown exceptional performance in complex reasoning tasks. However, these models often exhibit overthinking (generating redundant reasoning steps for simple problems), leading to excessive computational resource usage. While current mitigation strategies uniformly reduce reasoning tokens, they risk degrading performance on challenging tasks that require extended reasoning. This paper introduces Difficulty-Adaptive Slow Thinking (DAST), a novel framework that enables models to autonomously adjust the length of Chain-of-Thought (CoT) based on problem difficulty. We first propose a Token Length Budget (TLB) metric to quantify difficulty, then leverage budget-aware reward shaping and budget preference optimization to implement DAST. DAST penalizes overlong responses for simple tasks while incentivizing sufficient reasoning for complex problems. Experiments on diverse datasets and model scales demonstrate that DAST effectively mitigates overthinking (reducing token usage by over 30\% on average) while preserving reasoning accuracy on complex problems. Our codes and models are available at https://github.com/AnonymousUser0520/AnonymousRepo01.

Xiaolei Zhang, Yi Shen, Zhenhua Wang

Satellite power system is a complex, highly interconnected hybrid system that exhibit nonlinear and mode switching behaviors. Directed factor graph is an inference model for fault diagnosis using probabilistic reasoning techniques. A novel approach for constructing the directed factor graph structure based on hybrid bond graph model is proposed. The system components status and their fault symptoms are treated as hypothesis and evidences respectively. The cause-effect relations between hypothesis and evidences are identified and concluded though qualitative equations and causal path analysis on hybrid bond graph model. A power supply module of a satellite power system is provided as case study to show the feasibility and validity of the proposed method.

Xingwu Sun, Yanfeng Chen, Yiqing Huang et al. · tencent-ai

In this paper, we introduce Hunyuan-Large, which is currently the largest open-source Transformer-based mixture of experts model, with a total of 389 billion parameters and 52 billion activation parameters, capable of handling up to 256K tokens. We conduct a thorough evaluation of Hunyuan-Large's superior performance across various benchmarks including language understanding and generation, logical reasoning, mathematical problem-solving, coding, long-context, and aggregated tasks, where it outperforms LLama3.1-70B and exhibits comparable performance when compared to the significantly larger LLama3.1-405B model. Key practice of Hunyuan-Large include large-scale synthetic data that is orders larger than in previous literature, a mixed expert routing strategy, a key-value cache compression technique, and an expert-specific learning rate strategy. Additionally, we also investigate the scaling laws and learning rate schedule of mixture of experts models, providing valuable insights and guidances for future model development and optimization. The code and checkpoints of Hunyuan-Large are released to facilitate future innovations and applications. Codes: https://github.com/Tencent/Hunyuan-Large Models: https://huggingface.co/tencent/Tencent-Hunyuan-Large

Chao Yu, Yi Shen, Yue Mao et al.

Hierarchical Text Classification (HTC) is a challenging task where a document can be assigned to multiple hierarchically structured categories within a taxonomy. The majority of prior studies consider HTC as a flat multi-label classification problem, which inevitably leads to "label inconsistency" problem. In this paper, we formulate HTC as a sequence generation task and introduce a sequence-to-tree framework (Seq2Tree) for modeling the hierarchical label structure. Moreover, we design a constrained decoding strategy with dynamic vocabulary to secure the label consistency of the results. Compared with previous works, the proposed approach achieves significant and consistent improvements on three benchmark datasets.

Tianhao Xu, Yiming Liu, Xianglong Lu et al.

Optimizing Large Language Model (LLM) inference in production systems is increasingly difficult due to dynamic workloads, stringent latency/throughput targets, and a rapidly expanding configuration space. This complexity spans not only distributed parallelism strategies (tensor/pipeline/expert) but also intricate framework-specific runtime parameters such as those concerning the enablement of CUDA graphs, available KV-cache memory fractions, and maximum token capacity, which drastically impact performance. The diversity of modern inference frameworks (e.g., TRT-LLM, vLLM, SGLang), each employing distinct kernels and execution policies, makes manual tuning both framework-specific and computationally prohibitive. We present AIConfigurator, a unified performance-modeling system that enables rapid, framework-agnostic inference configuration search without requiring GPU-based profiling. AIConfigurator combines (1) a methodology that decomposes inference into analytically modelable primitives - GEMM, attention, communication, and memory operations while capturing framework-specific scheduling dynamics; (2) a calibrated kernel-level performance database for these primitives across a wide range of hardware platforms and popular open-weights models (GPT-OSS, Qwen, DeepSeek, LLama, Mistral); and (3) an abstraction layer that automatically resolves optimal launch parameters for the target backend, seamlessly integrating into production-grade orchestration systems. Evaluation on production LLM serving workloads demonstrates that AIConfigurator identifies superior serving configurations that improve performance by up to 40% for dense models (e.g., Qwen3-32B) and 50% for MoE architectures (e.g., DeepSeek-V3), while completing searches within 30 seconds on average. Enabling the rapid exploration of vast design spaces - from cluster topology down to engine specific flags.

Wenjing Zhang, Jiangze Yan, Jieyun Huang et al.

Distilling reasoning capabilities from Large Reasoning Models (LRMs) into smaller models is typically constrained by the limitation of rejection sampling. Standard methods treat the teacher as a static filter, discarding complex "corner-case" problems where the teacher fails to explore valid solutions independently, thereby creating an artificial "Teacher Ceiling" for the student. In this work, we propose Hindsight Entropy-Assisted Learning (HEAL), an RL-free framework designed to bridge this reasoning gap. Drawing on the educational theory of the Zone of Proximal Development(ZPD), HEAL synergizes three core modules: (1) Guided Entropy-Assisted Repair (GEAR), an active intervention mechanism that detects critical reasoning breakpoints via entropy dynamics and injects targeted hindsight hints to repair broken trajectories; (2) Perplexity-Uncertainty Ratio Estimator (PURE), a rigorous filtering protocol that decouples genuine cognitive breakthroughs from spurious shortcuts; and (3) Progressive Answer-guided Curriculum Evolution (PACE), a three-stage distillation strategy that organizes training from foundational alignment to frontier breakthrough. Extensive experiments on multiple benchmarks demonstrate that HEAL significantly outperforms traditional SFT distillation and other baselines.

Yixin Jin, Meiqi Wang, Meng Li et al.

In this paper, we describe our approaches to TREC Real-Time Summarization of Twitter. We focus on real time push notification scenario, which requires a system monitors the stream of sampled tweets and returns the tweets relevant and novel to given interest profiles. Dirichlet score with and with very little smoothing (baseline) are employed to classify whether a tweet is relevant to a given interest profile. Using metrics including Mean Average Precision (MAP, cumulative gain (CG) and discount cumulative gain (DCG), the experiment indicates that our approach has a good performance. It is also desired to remove the redundant tweets from the pushing queue. Due to the precision limit, we only describe the algorithm in this paper.

Xiangyu Li, Chenglin Wang, Qiantong Shen et al.

Ambiguous Medical Image Segmentation (AMIS) is significant to address the challenges of inherent uncertainties from image ambiguities, noise, and subjective annotations. Existing conditional variational autoencoder (cVAE)-based methods effectively capture uncertainty but face limitations including redundancy in high-dimensional latent spaces and limited expressiveness of single posterior networks. To overcome these issues, we introduce a novel PCA-Enhanced Probabilistic U-Net (\textbf{PEP U-Net}). Our method effectively incorporates Principal Component Analysis (PCA) for dimensionality reduction in the posterior network to mitigate redundancy and improve computational efficiency. Additionally, we further employ an inverse PCA operation to reconstruct critical information, enhancing the latent space's representational capacity. Compared to conventional generative models, our method preserves the ability to generate diverse segmentation hypotheses while achieving a superior balance between segmentation accuracy and predictive variability, thereby advancing the performance of generative modeling in medical image segmentation.

Enbo Zhao, Yi Shen, Shuming Shi et al.

Recently, there is a high demand for deploying DeepSeek-R1 and V3 locally, possibly because the official service often suffers from being busy and some organizations have data privacy concerns. While single-machine deployment offers infrastructure simplicity, the models' 671B FP8 parameter configuration exceeds the practical memory limits of a standard 8-GPU machine. Quantization is a widely used technique that helps reduce model memory consumption. However, it is unclear what the performance of DeepSeek-R1 and V3 will be after being quantized. This technical report presents the first quantitative evaluation of multi-bitwidth quantization across the complete DeepSeek model spectrum. Key findings reveal that 4-bit quantization maintains little performance degradation versus FP8 while enabling single-machine deployment on standard NVIDIA GPU devices. We further propose DQ3_K_M, a dynamic 3-bit quantization method that significantly outperforms traditional Q3_K_M variant on various benchmarks, which is also comparable with 4-bit quantization (Q4_K_M) approach in most tasks. Moreover, DQ3_K_M supports single-machine deployment configurations for both NVIDIA H100/A100 and Huawei 910B. Our implementation of DQ3\_K\_M is released at https://github.com/UnicomAI/DeepSeek-Eval, containing optimized 3-bit quantized variants of both DeepSeek-R1 and DeepSeek-V3.

Yi Shen, Shao Gu

Recently, interesting empirical phenomena known as Neural Collapse have been observed during the final phase of training deep neural networks for classification tasks. We examine this issue when the feature dimension d is equal to the number of classes K. We demonstrate that two popular unconstrained feature models are strict saddle functions, with every critical point being either a global minimum or a strict saddle point that can be exited using negative curvatures. The primary findings conclusively confirm the conjecture on the unconstrained feature models in previous articles.

Chang Zhou, Yang Zhao, Jin Cao et al.

This paper explores the integration of strategic optimization methods in search advertising, focusing on ad ranking and bidding mechanisms within E-commerce platforms. By employing a combination of reinforcement learning and evolutionary strategies, we propose a dynamic model that adjusts to varying user interactions and optimizes the balance between advertiser cost, user relevance, and platform revenue. Our results suggest significant improvements in ad placement accuracy and cost efficiency, demonstrating the model's applicability in real-world scenarios.

Jialiang Wu, Yi Shen, Ziheng Zhang et al.

Emotion-Cause Pair Extraction (ECPE) involves extracting clause pairs representing emotions and their causes in a document. Existing methods tend to overfit spurious correlations, such as positional bias in existing benchmark datasets, rather than capturing semantic features. Inspired by recent work, we explore leveraging large language model (LLM) to address ECPE task without additional training. Despite strong capabilities, LLMs suffer from uncontrollable outputs, resulting in mediocre performance. To address this, we introduce chain-of-thought to mimic human cognitive process and propose the Decomposed Emotion-Cause Chain (DECC) framework. Combining inducing inference and logical pruning, DECC guides LLMs to tackle ECPE task. We further enhance the framework by incorporating in-context learning. Experiment results demonstrate the strength of DECC compared to state-of-the-art supervised fine-tuning methods. Finally, we analyze the effectiveness of each component and the robustness of the method in various scenarios, including different LLM bases, rebalanced datasets, and multi-pair extraction.

Zhicheng Ma, Xiang Liu, Zhaoxiang Liu et al.

Large Language Models (LLMs) based on Mixture-of-Experts (MoE) are pivotal in industrial applications for their ability to scale performance efficiently. However, standard MoEs enforce uniform expert sizes,creating a rigidity that fails to align computational costs with varying token-level complexity. While heterogeneous expert architectures attempt to address this by diversifying expert sizes, they often suffer from significant system-level challenges, specifically unbalanced GPU utilization and inefficient parameter utilization, which hinder practical deployment. To bridge the gap between theoretical heterogeneity and robust industrial application, we propose Mixture of Heterogeneous Grouped Experts (MoHGE) which introduces a two-level routing mechanism to enable flexible, resource-aware expert combinations. To optimize inference efficiency, we propose a Group-Wise Auxiliary Loss, which dynamically steers tokens to the most parameter-efficient expert groups based on task difficulty. To address the critical deployment challenge of GPU load balancing, we introduce an All-size Group-decoupling Allocation strategy coupled with an Intra-Group Experts Auxiliary Loss. These mechanisms collectively ensure uniform computation distribution across GPUs. Extensive evaluations demonstrate that MoHGE matches the performance of MoE architectures while reducing the total parameters by approximately 20% and maintaining balanced GPU utilization. Our work establishes a scalable paradigm for resource-efficient MoE design, offering a practical solution for optimizing inference costs in real-world scenarios.

Qiping Lai, Yi Shen, Chen Shen

In high-penetration renewable power systems with complex and highly variable operating scenarios, grid-connected inverters (GCIs) may transition between different control modes to adapt to diverse grid conditions. Among these, the switching between grid-following (GFL) and grid-forming (GFM) control modes is particularly critical. Nevertheless, safe and robust GFL-GFM switching control strategies for GCIs remain largely unexplored. To overcome this challenge, this paper establishes a full-order small-signal state-space model for the GFL-GFM switched system, precisely reflecting all internal circuit and control dynamics. Subsequently, the small-signal security region (SSSR) of the switched system is defined and characterized, followed by an in-depth investigation into the multi-parameter impacts on the SSSRs and internal stability margin distributions (ISMDs). Furthermore, a novel comprehensive stability index (CSI) is proposed by integrating the stability margin, parameter sensitivity, and boundary distance. Based on this CSI, a multi-objective adaptive GFL-GFM switching control strategy is designed to guarantee the dynamic security and robustness of the system. Finally, the proposed SSSR analysis method for the GFL-GFM switched system and the designed CSI-based switching control mechanism are validated through electromagnetic transient (EMT) simulations.

Yi Shen, Rihui Lan, Hua Wang

We propose first-order pressure-correction scheme for the incompressible Navier-Stokes equations, incorporating the recently developed the Dynamically Regularized Lagrange Multiplier (DRLM) methods. The resulting algorithms are fully decoupled and require solving only Poisson-type equations at each time step. Moreover, it exhibits unconditional energy stability. This paper provides a rigorous error analysis for the first-order scheme, establishing optimal error estimates for both velocity and pressure. Specifically, we employ mathematical induction to derive sharp velocity error bounds, while leveraging the inf-sup condition to prove optimal convergence rate for the pressure. To validate our theoretical findings, we present two numerical experiments demonstrating the accuracy and robustness of the method.

Jialiang Wu, Yi Shen, Sijia Liu et al.

Despite their impressive capacities, Large language models (LLMs) often struggle with the hallucination issue of generating inaccurate or fabricated content even when they possess correct knowledge. In this paper, we extend the exploration of the correlation between hidden-state prediction changes and output factuality into a deeper, token-wise level. Based on the insights , we propose cross-layer Entropy eNhanced Decoding (END), a decoding method that mitigates hallucinations without requiring extra training. END leverages inner probability changes across layers to individually quantify the factual knowledge required for each candidate token, and adjusts the final predicting distribution to prioritize tokens with higher factuality. Experiments on both hallucination and QA benchmarks demonstrate that END significantly enhances the truthfulness and informativeness of generated content while maintaining robust QA accuracy. Moreover, our work provides a deeper perspective on understanding the correlations between inherent knowledge and output factuality.

Xenia Konti, Yi Shen, Zifan Wang et al.

The performance of machine learning (ML) models critically depends on the quality and representativeness of the training data. In applications with multiple heterogeneous data generating sources, standard ML methods often learn spurious correlations that perform well on average but degrade performance for atypical or underrepresented groups. Prior work addresses this issue by optimizing the worst-group performance. However, these approaches typically assume that the underlying data distributions for each group can be accurately estimated using the training data, a condition that is frequently violated in noisy, non-stationary, and evolving environments. In this work, we propose a novel framework that relies on Wasserstein-based distributionally robust optimization (DRO) to account for the distributional uncertainty within each group, while simultaneously preserving the objective of improving the worst-group performance. We develop a gradient descent-ascent algorithm to solve the proposed DRO problem and provide convergence results. Finally, we validate the effectiveness of our method on real-world data.

Simindokht Jahangard, Mehrzad Mohammadi, Yi Shen et al.

Recent advances in Vision-Language Models (VLMs) and large language models (LLMs) have greatly enhanced visual reasoning, a key capability for embodied AI agents like robots. However, existing visual reasoning benchmarks often suffer from several limitations: they lack a clear definition of reasoning complexity, offer have no control to generate questions over varying difficulty and task customization, and fail to provide structured, step-by-step reasoning annotations (workflows). To bridge these gaps, we formalize reasoning complexity, introduce an adaptive query engine that generates customizable questions of varying complexity with detailed intermediate annotations, and extend the JRDB dataset with human-object interaction and geometric relationship annotations to create JRDB-Reasoning, a benchmark tailored for visual reasoning in human-crowded environments. Our engine and benchmark enable fine-grained evaluation of visual reasoning frameworks and dynamic assessment of visual-language models across reasoning levels.

Kavinayan P. Sivakumar, Yi Shen, Zachary Bell et al.

In this paper, we study an inverse reinforcement learning problem that involves learning the reward function of a learning agent using trajectory data collected while this agent is learning its optimal policy. To address this problem, we propose an inverse reinforcement learning method that allows us to estimate the policy parameters of the learning agent which can then be used to estimate its reward function. Our method relies on a new variant of the behavior cloning algorithm, which we call bundle behavior cloning, and uses a small number of trajectories generated by the learning agent's policy at different points in time to learn a set of policies that match the distribution of actions observed in the sampled trajectories. We then use the cloned policies to train a neural network model that estimates the reward function of the learning agent. We provide a theoretical analysis to show a complexity result on bound guarantees for our method that beats standard behavior cloning as well as numerical experiments for a reinforcement learning problem that validate the proposed method.

Yuan Zhuang, Yi Shen, Yuexin Bian et al.

Recent studies have shown that combining parameter-efficient fine-tuning (PEFT) with mixture-of-experts (MoE) is an effective strategy for adapting large language models (LLMs) to the downstream tasks. However, most existing approaches rely on conventional TopK routing, which requires careful hyperparameter tuning and assigns a fixed number of experts to each token. In this work, we propose LD-MoLE, a Learnable Dynamic routing mechanism for Mixture of LoRA Experts that enables adaptive, token-dependent, and layer-wise expert allocation. Our method replaces the non-differentiable TopK selection with a differentiable routing function and a closed-form solution. Moreover, our design allows the model to adaptively determine the number of experts to activate for each token at different layers. In addition, we introduce an analytical sparsity control objective to regularize the number of activated experts. Extensive experiments on the Qwen3-1.7B and Llama-3.2-3B models show that LD-MoLE achieves the highest average scores compared to state-of-the-art baselines, across a diverse set of benchmarks. Our method not only achieves superior performance, but also demonstrates the ability to learn token-dependent and layer-wise expert allocation.

Pengxi Liu, Yi Shen, Matthew M. Engelhard et al.

Fairness metrics utilizing the area under the receiver operator characteristic curve (AUC) have gained increasing attention in high-stakes domains such as healthcare, finance, and criminal justice. In these domains, fairness is often evaluated over risk scores rather than binary outcomes, and a common challenge is that enforcing strict fairness can significantly degrade AUC performance. To address this challenge, we propose Fair Proportional Optimal Transport (FairPOT), a novel, model-agnostic post-processing framework that strategically aligns risk score distributions across different groups using optimal transport, but does so selectively by transforming a controllable proportion, i.e., the top-lambda quantile, of scores within the disadvantaged group. By varying lambda, our method allows for a tunable trade-off between reducing AUC disparities and maintaining overall AUC performance. Furthermore, we extend FairPOT to the partial AUC setting, enabling fairness interventions to concentrate on the highest-risk regions. Extensive experiments on synthetic, public, and clinical datasets show that FairPOT consistently outperforms existing post-processing techniques in both global and partial AUC scenarios, often achieving improved fairness with slight AUC degradation or even positive gains in utility. The computational efficiency and practical adaptability of FairPOT make it a promising solution for real-world deployment.

Andreas Kontogiannis, Konstantinos Papathanasiou, Yi Shen et al.

Learning to cooperate in distributed partially observable environments with no communication abilities poses significant challenges for multi-agent deep reinforcement learning (MARL). This paper addresses key concerns in this domain, focusing on inferring state representations from individual agent observations and leveraging these representations to enhance agents' exploration and collaborative task execution policies. To this end, we propose a novel state modelling framework for cooperative MARL, where agents infer meaningful belief representations of the non-observable state, with respect to optimizing their own policies, while filtering redundant and less informative joint state information. Building upon this framework, we propose the MARL SMPE algorithm. In SMPE, agents enhance their own policy's discriminative abilities under partial observability, explicitly by incorporating their beliefs into the policy network, and implicitly by adopting an adversarial type of exploration policies which encourages agents to discover novel, high-value states while improving the discriminative abilities of others. Experimentally, we show that SMPE outperforms state-of-the-art MARL algorithms in complex fully cooperative tasks from the MPE, LBF, and RWARE benchmarks.

Yi Shen, Hanyan Huang

Offline reinforcement learning has received extensive attention from scholars because it avoids the interaction between the agent and the environment by learning a policy through a static dataset. However, general reinforcement learning methods cannot get satisfactory results in offline reinforcement learning due to the out-of-distribution state actions that the dataset cannot cover during training. To solve this problem, the policy regularization method that tries to directly clone policies used in static datasets has received numerous studies due to its simplicity and effectiveness. However, policy constraint methods make the agent choose the corresponding actions in the static dataset. This type of constraint is usually over-conservative, which results in suboptimal policies, especially in low-quality static datasets. In this paper, a hypercube policy regularization framework is proposed, this method alleviates the constraints of policy constraint methods by allowing the agent to explore the actions corresponding to similar states in the static dataset, which increases the effectiveness of algorithms in low-quality datasets. It was also theoretically demonstrated that the hypercube policy regularization framework can effectively improve the performance of original algorithms. In addition, the hypercube policy regularization framework is combined with TD3-BC and Diffusion-QL for experiments on D4RL datasets which are called TD3-BC-C and Diffusion-QL-C. The experimental results of the score demonstrate that TD3-BC-C and Diffusion-QL-C perform better than state-of-the-art algorithms like IQL, CQL, TD3-BC and Diffusion-QL in most D4RL environments in approximate time.

Yi Shen, Hanyan Huang

Offline reinforcement learning learns from a static dataset without interacting with environments, which ensures security and thus owns a good application prospect. However, directly applying naive reinforcement learning algorithm usually fails in an offline environment due to inaccurate Q value approximation caused by out-of-distribution (OOD) state-actions. It is an effective way to solve this problem by penalizing the Q-value of OOD state-actions. Among the methods of punishing OOD state-actions, count-based methods have achieved good results in discrete domains in a simple form. Inspired by it, a novel pseudo-count method for continuous domains called Grid-Mapping Pseudo-Count method (GPC) is proposed by extending the count-based method from discrete to continuous domains. Firstly, the continuous state and action space are mapped to discrete space using Grid-Mapping, then the Q-values of OOD state-actions are constrained through pseudo-count. Secondly, the theoretical proof is given to show that GPC can obtain appropriate uncertainty constraints under fewer assumptions than other pseudo-count methods. Thirdly, GPC is combined with Soft Actor-Critic algorithm (SAC) to get a new algorithm called GPC-SAC. Lastly, experiments on D4RL datasets are given to show that GPC-SAC has better performance and less computational cost than other algorithms that constrain the Q-value.

Lin Yang, Yi Shen, Yue Mao et al.

Emotion recognition in conversation (ERC) aims to detect the emotion label for each utterance. Motivated by recent studies which have proven that feeding training examples in a meaningful order rather than considering them randomly can boost the performance of models, we propose an ERC-oriented hybrid curriculum learning framework. Our framework consists of two curricula: (1) conversation-level curriculum (CC); and (2) utterance-level curriculum (UC). In CC, we construct a difficulty measurer based on "emotion shift" frequency within a conversation, then the conversations are scheduled in an "easy to hard" schema according to the difficulty score returned by the difficulty measurer. For UC, it is implemented from an emotion-similarity perspective, which progressively strengthens the model's ability in identifying the confusing emotions. With the proposed model-agnostic hybrid curriculum learning strategy, we observe significant performance boosts over a wide range of existing ERC models and we are able to achieve new state-of-the-art results on four public ERC datasets.

Chenyu Liu, Yan Zhang, Yi Shen et al.

In this paper, we consider a transfer Reinforcement Learning (RL) problem in continuous state and action spaces, under unobserved contextual information. For example, the context can represent the mental view of the world that an expert agent has formed through past interactions with this world. We assume that this context is not accessible to a learner agent who can only observe the expert data. Then, our goal is to use the context-aware expert data to learn an optimal context-unaware policy for the learner using only a few new data samples. Such problems are typically solved using imitation learning that assumes that both the expert and learner agents have access to the same information. However, if the learner does not know the expert context, using the expert data alone will result in a biased learner policy and will require many new data samples to improve. To address this challenge, in this paper, we formulate the learning problem as a causal bound-constrained Multi-Armed-Bandit (MAB) problem. The arms of this MAB correspond to a set of basis policy functions that can be initialized in an unsupervised way using the expert data and represent the different expert behaviors affected by the unobserved context. On the other hand, the MAB constraints correspond to causal bounds on the accumulated rewards of these basis policy functions that we also compute from the expert data. The solution to this MAB allows the learner agent to select the best basis policy and improve it online. And the use of causal bounds reduces the exploration variance and, therefore, improves the learning rate. We provide numerical experiments on an autonomous driving example that show that our proposed transfer RL method improves the learner's policy faster compared to existing imitation learning methods and enjoys much lower variance during training.

Qiumei Cheng, Yi Shen, Dezhang Kong et al.

Network security events prediction helps network operators to take response strategies from a proactive perspective, and reduce the cost caused by network attacks, which is of great significance for maintaining the security of the entire network. Most of the existing event prediction methods rely on temporal characteristics and are dedicated to exploring time series predictions, but ignoring the spatial relationship between hosts. This paper combines the temporal and spatial characteristics of security events and proposes a spatial-temporal event prediction model, named STEP. In particular, STEP formulates the security events prediction into a spatial-temporal sequence prediction. STEP utilizes graph convolution operation to capture the spatial characteristics of hosts in the network, and adopts the long short term memory (LSTM) to capture the dynamic temporal dependency of events. This paper verifies the proposed STEP scheme on two public data sets. The experimental results show that the prediction accuracy of security events under STEP is higher than that of benchmark models such as LSTM, ConvLSTM. Besides, STEP achieves high prediction accuracy when we predict events from different lengths of sequence.

Qiumei Cheng, Shiying Zhou, Yi Shen et al.

The surge in the internet of things (IoT) devices seriously threatens the current IoT security landscape, which requires a robust network intrusion detection system (NIDS). Despite superior detection accuracy, existing machine learning or deep learning based NIDS are vulnerable to adversarial examples. Recently, generative adversarial networks (GANs) have become a prevailing method in adversarial examples crafting. However, the nature of discrete network traffic at the packet level makes it hard for GAN to craft adversarial traffic as GAN is efficient in generating continuous data like image synthesis. Unlike previous methods that convert discrete network traffic into a grayscale image, this paper gains inspiration from SeqGAN in sequence generation with policy gradient. Based on the structure of SeqGAN, we propose Attack-GAN to generate adversarial network traffic at packet level that complies with domain constraints. Specifically, the adversarial packet generation is formulated into a sequential decision making process. In this case, each byte in a packet is regarded as a token in a sequence. The objective of the generator is to select a token to maximize its expected end reward. To bypass the detection of NIDS, the generated network traffic and benign traffic are classified by a black-box NIDS. The prediction results returned by the NIDS are fed into the discriminator to guide the update of the generator. We generate malicious adversarial traffic based on a real public available dataset with attack functionality unchanged. The experimental results validate that the generated adversarial samples are able to deceive many existing black-box NIDS.

Yue Mao, Yi Shen, Chao Yu et al.

Aspect based sentiment analysis (ABSA) involves three fundamental subtasks: aspect term extraction, opinion term extraction, and aspect-level sentiment classification. Early works only focused on solving one of these subtasks individually. Some recent work focused on solving a combination of two subtasks, e.g., extracting aspect terms along with sentiment polarities or extracting the aspect and opinion terms pair-wisely. More recently, the triple extraction task has been proposed, i.e., extracting the (aspect term, opinion term, sentiment polarity) triples from a sentence. However, previous approaches fail to solve all subtasks in a unified end-to-end framework. In this paper, we propose a complete solution for ABSA. We construct two machine reading comprehension (MRC) problems and solve all subtasks by joint training two BERT-MRC models with parameters sharing. We conduct experiments on these subtasks, and results on several benchmark datasets demonstrate the effectiveness of our proposed framework, which significantly outperforms existing state-of-the-art methods.

Pengxu Wei, Hannan Lu, Radu Timofte et al.

This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020. This challenge involves three tracks to super-resolve an input image for $\times$2, $\times$3 and $\times$4 scaling factors, respectively. The goal is to attract more attention to realistic image degradation for the SR task, which is much more complicated and challenging, and contributes to real-world image super-resolution applications. 452 participants were registered for three tracks in total, and 24 teams submitted their results. They gauge the state-of-the-art approaches for real image SR in terms of PSNR and SSIM.

Hang Zhao, Jiyang Gao, Tian Lan et al.

Predicting the future behavior of moving agents is essential for real world applications. It is challenging as the intent of the agent and the corresponding behavior is unknown and intrinsically multimodal. Our key insight is that for prediction within a moderate time horizon, the future modes can be effectively captured by a set of target states. This leads to our target-driven trajectory prediction (TNT) framework. TNT has three stages which are trained end-to-end. It first predicts an agent's potential target states $T$ steps into the future, by encoding its interactions with the environment and the other agents. TNT then generates trajectory state sequences conditioned on targets. A final stage estimates trajectory likelihoods and a final compact set of trajectory predictions is selected. This is in contrast to previous work which models agent intents as latent variables, and relies on test-time sampling to generate diverse trajectories. We benchmark TNT on trajectory prediction of vehicles and pedestrians, where we outperform state-of-the-art on Argoverse Forecasting, INTERACTION, Stanford Drone and an in-house Pedestrian-at-Intersection dataset.

Zhuohuang Zhang, Donald S. Williamson, Yi Shen

Phase serves as a critical component of speech that influences the quality and intelligibility. Current speech enhancement algorithms are beginning to address phase distortions, but the algorithms focus on normal-hearing (NH) listeners. It is not clear whether phase enhancement is beneficial for hearing-impaired (HI) listeners. We investigated the influence of phase distortion on speech quality through a listening study, in which NH and HI listeners provided speech-quality ratings using the MUSHRA procedure. In one set of conditions, the speech was mixed with babble noise at 4 different signal-to-noise ratios (SNRs) from -5 to 10 dB. In another set of conditions, the SNR was fixed at 10 dB and the noisy speech was presented in a simulated reverberant room with T60s ranging from 100 to 1000 ms. The speech level was kept at 65 dB SPL for NH listeners and amplification was applied for HI listeners to ensure audibility. Ideal ratio masking (IRM) was used to simulate speech enhancement. Two objective metrics (i.e., PESQ and HASQI) were utilized to compare subjective and objective ratings. Results indicate that phase distortion has a negative impact on perceived quality for both groups and PESQ is more closely correlated with human ratings.

Zhuohuang Zhang, Chengyun Deng, Yi Shen et al.

Recent work has shown that it is feasible to use generative adversarial networks (GANs) for speech enhancement, however, these approaches have not been compared to state-of-the-art (SOTA) non GAN-based approaches. Additionally, many loss functions have been proposed for GAN-based approaches, but they have not been adequately compared. In this study, we propose novel convolutional recurrent GAN (CRGAN) architectures for speech enhancement. Multiple loss functions are adopted to enable direct comparisons to other GAN-based systems. The benefits of including recurrent layers are also explored. Our results show that the proposed CRGAN model outperforms the SOTA GAN-based models using the same loss functions and it outperforms other non-GAN based systems, indicating the benefits of using a GAN for speech enhancement. Overall, the CRGAN model that combines an objective metric loss function with the mean squared error (MSE) provides the best performance over comparison approaches across many evaluation metrics.

Jiyang Gao, Chen Sun, Hang Zhao et al.

Behavior prediction in dynamic, multi-agent systems is an important problem in the context of self-driving cars, due to the complex representations and interactions of road components, including moving agents (e.g. pedestrians and vehicles) and road context information (e.g. lanes, traffic lights). This paper introduces VectorNet, a hierarchical graph neural network that first exploits the spatial locality of individual road components represented by vectors and then models the high-order interactions among all components. In contrast to most recent approaches, which render trajectories of moving agents and road context information as bird-eye images and encode them with convolutional neural networks (ConvNets), our approach operates on a vector representation. By operating on the vectorized high definition (HD) maps and agent trajectories, we avoid lossy rendering and computationally intensive ConvNet encoding steps. To further boost VectorNet's capability in learning context features, we propose a novel auxiliary task to recover the randomly masked out map entities and agent trajectories based on their context. We evaluate VectorNet on our in-house behavior prediction benchmark and the recently released Argoverse forecasting dataset. Our method achieves on par or better performance than the competitive rendering approach on both benchmarks while saving over 70% of the model parameters with an order of magnitude reduction in FLOPs. It also outperforms the state of the art on the Argoverse dataset.

Zhe Liu, Hesheng Wang, Shunbo Zhou et al.

In this paper, we focus on the problem of task allocation, cooperative path planning and motion coordination of the large-scale system with thousands of robots, aiming for practical applications in robotic warehouses and automated logistics systems. Particularly, we solve the life-long planning problem and guarantee the coordination performance of large-scale robot network in the presence of robot motion uncertainties and communication failures. A hierarchical planning and coordination structure is presented. The environment is divided into several sectors and a dynamic traffic heat-map is generated to describe the current sector-level traffic flow. In task planning level, a greedy task allocation method is implemented to assign the current task to the nearest free robot and the sector-level path is generated by comprehensively considering the traveling distance, the traffic heat-value distribution and the current robot/communication failures. In motion coordination level, local cooperative A* algorithm is implemented in each sector to generate the collision-free road-level path of each robot in the sector and the rolling planning structure is introduced to solve problems caused by motion and communication uncertainties. The effectiveness and practical applicability of the proposed approach are validated by large-scale simulations with more than one thousand robots and real laboratory experiments.

Yue Mao, Yi Shen, Gang Qin et al.

Predicting the popularity of online videos is important for video streaming content providers. This is a challenging problem because of the following two reasons. First, the problem is both "wide" and "deep". That is, it not only depends on a wide range of features, but also be highly non-linear and complex. Second, multiple competitors may be involved. In this paper, we propose a general prediction model using the multi-task learning (MTL) module and the relation network (RN) module, where MTL can reduce over-fitting and RN can model the relations of multiple competitors. Experimental results show that our proposed approach significantly increases the accuracy on predicting the total view counts of TV series with RN and MTL modules.

Yi Shen, Bin Han, Elena Braverman

In this paper we are particularly interested in the image inpainting problem using directional complex tight wavelet frames. Under the assumption that frame coefficients of images are sparse, several iterative thresholding algorithms for the image inpainting problem have been proposed in the literature. The outputs of such iterative algorithms are closely linked to solutions of several convex minimization models using the balanced approach which simultaneously combines the $l_1$-regularization for sparsity of frame coefficients and the $l_2$-regularization for smoothness of the solution. Due to the redundancy of a tight frame, elements of a tight frame could be highly correlated and therefore, their corresponding frame coefficients of an image are expected to close to each other. This is called the grouping effect in statistics. In this paper, we establish the grouping effect property for frame-based convex minimization models using the balanced approach. This result on grouping effect partially explains the effectiveness of models using the balanced approach for several image restoration problems. Inspired by recent development on directional tensor product complex tight framelets (TP-CTFs) and their impressive performance for the image denoising problem, in this paper we propose an iterative thresholding algorithm using a single tight frame derived from TP-CTFs for the image inpainting problem. Experimental results show that our proposed algorithm can handle well both cartoons and textures simultaneously and performs comparably and often better than several well-known frame-based iterative thresholding algorithms for the image inpainting problem without noise. For the image inpainting problem with additive zero-mean i.i.d. Gaussian noise, our proposed algorithm using TP-CTFs performs superior than other known state-of-the-art frame-based image inpainting algorithms.