Guan Wang

Guan Wang, Sijie Cheng, Xianyuan Zhan et al. · tsinghua

Nowadays, open-source large language models like LLaMA have emerged. Recent developments have incorporated supervised fine-tuning (SFT) and reinforcement learning fine-tuning (RLFT) to align these models with human goals. However, SFT methods treat all training data with mixed quality equally, while RLFT methods require high-quality pairwise or ranking-based preference data. In this study, we present a novel framework, named OpenChat, to advance open-source language models with mixed-quality data. Specifically, we consider the general SFT training data, consisting of a small amount of expert data mixed with a large proportion of sub-optimal data, without any preference labels. We propose the C(onditioned)-RLFT, which regards different data sources as coarse-grained reward labels and learns a class-conditioned policy to leverage complementary data quality information. Interestingly, the optimal policy in C-RLFT can be easily solved through single-stage, RL-free supervised learning, which is lightweight and avoids costly human preference labeling. Through extensive experiments on three standard benchmarks, our openchat-13b fine-tuned with C-RLFT achieves the highest average performance among all 13b open-source language models. Moreover, we use AGIEval to validate the model generalization performance, in which only openchat-13b surpasses the base model. Finally, we conduct a series of analyses to shed light on the effectiveness and robustness of OpenChat. Our code, data, and models are publicly available at https://github.com/imoneoi/openchat and https://huggingface.co/openchat.

Longbin Ji, Guan Wang, Xuan Wei et al.

Joint audio-video generation aims to synthesize temporally synchronized and semantically coherent visual-acoustic content. However, existing open-source methods mainly rely on either dual-tower designs with posterior alignment or fully unified tri-modal designs that mix textual context, audio and video in one shared space. The former weakens fine-grained audio-video co-evolution, while the latter couples semantic conditioning with low-level synchronization. To address these limitations, we propose NAVA, a Native Audio-Visual Alignment framework for joint audio-video generation. NAVA is built upon context-conditioned native audio-visual alignment: it first establishes audio-video correspondence in a dedicated interaction space, and then uses external context to condition the joint denoising process. Specifically, NAVA is instantiated with an Align-then-Fuse MMDiT architecture, which transitions from modality-aware audio-video alignment to modality-shared joint denoising. Furthermore, we introduce Timbre-in-Context Conditioning to associate reference timbre cues with corresponding speech spans to achieve controllable speech timbre. Experiments on Verse-Bench and Seed-TTS, together with a user study, demonstrate that NAVA achieves superior video quality, precise audio-visual synchronization, competitive audio quality, and stronger reference-timbre controllability using only 6.3B parameters.

Guan Wang, Shuyin Xia, Lei Qian et al.

Graph Convolutional Network (GCN) is a model that can effectively handle graph data tasks and has been successfully applied. However, for large-scale graph datasets, GCN still faces the challenge of high computational overhead, especially when the number of convolutional layers in the graph is large. Currently, there are many advanced methods that use various sampling techniques or graph coarsening techniques to alleviate the inconvenience caused during training. However, among these methods, some ignore the multi-granularity information in the graph structure, and the time complexity of some coarsening methods is still relatively high. In response to these issues, based on our previous work, in this paper, we propose a new framework called Efficient and Scalable Granular-ball Graph Coarsening Method for Large-scale Graph Node Classification. Specifically, this method first uses a multi-granularity granular-ball graph coarsening algorithm to coarsen the original graph to obtain many subgraphs. The time complexity of this stage is linear and much lower than that of the exiting graph coarsening methods. Then, subgraphs composed of these granular-balls are randomly sampled to form minibatches for training GCN. Our algorithm can adaptively and significantly reduce the scale of the original graph, thereby enhancing the training efficiency and scalability of GCN. Ultimately, the experimental results of node classification on multiple datasets demonstrate that the method proposed in this paper exhibits superior performance. The code is available at https://anonymous.4open.science/r/1-141D/.

Tahmina Khanam, Hamid Laga, Mohammed Bennamoun et al.

We propose the first comprehensive approach for modeling and analyzing the spatiotemporal shape variability in tree-like 4D objects, i.e., 3D objects whose shapes bend, stretch, and change in their branching structure over time as they deform, grow, and interact with their environment. Our key contribution is the representation of tree-like 3D shapes using Square Root Velocity Function Trees (SRVFT). By solving the spatial registration in the SRVFT space, which is equipped with an L2 metric, 4D tree-shaped structures become time-parameterized trajectories in this space. This reduces the problem of modeling and analyzing 4D tree-like shapes to that of modeling and analyzing elastic trajectories in the SRVFT space, where elasticity refers to time warping. In this paper, we propose a novel mathematical representation of the shape space of such trajectories, a Riemannian metric on that space, and computational tools for fast and accurate spatiotemporal registration and geodesics computation between 4D tree-shaped structures. Leveraging these building blocks, we develop a full framework for modelling the spatiotemporal variability using statistical models and generating novel 4D tree-like structures from a set of exemplars. We demonstrate and validate the proposed framework using real 4D plant data.

Haifeng Wang, Hua Wu, Tian Wu et al.

In this report, we introduce ERNIE 5.0, a natively autoregressive foundation model desinged for unified multimodal understanding and generation across text, image, video, and audio. All modalities are trained from scratch under a unified next-group-of-tokens prediction objective, based on an ultra-sparse mixture-of-experts (MoE) architecture with modality-agnostic expert routing. To address practical challenges in large-scale deployment under diverse resource constraints, ERNIE 5.0 adopts a novel elastic training paradigm. Within a single pre-training run, the model learns a family of sub-models with varying depths, expert capacities, and routing sparsity, enabling flexible trade-offs among performance, model size, and inference latency in memory- or time-constrained scenarios. Moreover, we systematically address the challenges of scaling reinforcement learning to unified foundation models, thereby guaranteeing efficient and stable post-training under ultra-sparse MoE architectures and diverse multimodal settings. Extensive experiments demonstrate that ERNIE 5.0 achieves strong and balanced performance across multiple modalities. To the best of our knowledge, among publicly disclosed models, ERNIE 5.0 represents the first production-scale realization of a trillion-parameter unified autoregressive model that supports both multimodal understanding and generation. To facilitate further research, we present detailed visualizations of modality-agnostic expert routing in the unified model, alongside comprehensive empirical analysis of elastic training, aiming to offer profound insights to the community.

Yibo Wang, Congying Xia, Guan Wang et al.

The explosion of e-commerce has caused the need for processing and analysis of product titles, like entity typing in product titles. However, the rapid activity in e-commerce has led to the rapid emergence of new entities, which is difficult to be solved by general entity typing. Besides, product titles in e-commerce have very different language styles from text data in general domain. In order to handle new entities in product titles and address the special language styles problem of product titles in e-commerce domain, we propose our textual entailment model with continuous prompt tuning based hypotheses and fusion embeddings for e-commerce entity typing. First, we reformulate the entity typing task into a textual entailment problem to handle new entities that are not present during training. Second, we design a model to automatically generate textual entailment hypotheses using a continuous prompt tuning method, which can generate better textual entailment hypotheses without manual design. Third, we utilize the fusion embeddings of BERT embedding and CharacterBERT embedding with a two-layer MLP classifier to solve the problem that the language styles of product titles in e-commerce are different from that of general domain. To analyze the effect of each contribution, we compare the performance of entity typing and textual entailment model, and conduct ablation studies on continuous prompt tuning and fusion embeddings. We also evaluate the impact of different prompt template initialization for the continuous prompt tuning. We show our proposed model improves the average F1 score by around 2% compared to the baseline BERT entity typing model.

Shuyin Xia, Xinyu Lin, Guan Wang et al.

Optimization problems aim to find the optimal solution, which is becoming increasingly complex and difficult to solve. Traditional evolutionary optimization methods always overlook the granular characteristics of solution space. In the real scenario of numerous optimizations, the solution space is typically partitioned into sub-regions characterized by varying degree distributions. These sub-regions present different granularity characteristics at search potential and difficulty. Considering the granular characteristics of the solution space, the number of coarse-grained regions is smaller than the number of points, so the calculation is more efficient. On the other hand, coarse-grained characteristics are not easily affected by fine-grained sample points, so the calculation is more robust. To this end, this paper proposes a new multi-granularity evolutionary optimization method, namely the Granular-ball Optimization (GBO) algorithm, which characterizes and searches the solution space from coarse to fine. Specifically, using granular-balls instead of traditional points for optimization increases the diversity and robustness of the random search process. At the same time, the search range in different iteration processes is limited by the radius of granular-balls, covering the solution space from large to small. The mechanism of granular-ball splitting is applied to continuously split and evolve the large granular-balls into smaller ones for refining the solution space. Extensive experiments on commonly used benchmarks have shown that GBO outperforms popular and advanced evolutionary algorithms. The code can be found in the supporting materials.

Jiarui Ji, Zehua Zhang, Zhewei Wei et al.

Large language models (LLMs) have shown promise in simulating human-like social behaviors. Social graphs provide high-quality supervision signals that encode both local interactions and global network structure, yet they remain underutilized for LLM training. To address this gap, we propose Graphia, the first general LLM-based social graph simulation framework that leverages graph data as supervision for LLM post-training via reinforcement learning. With GNN-based structural rewards, Graphia trains specialized agents to predict whom to interact with (destination selection) and how to interact (edge generation), followed by designed graph generation pipelines. We evaluate Graphia under two settings: Transductive Dynamic Graph Generation (TDGG), a micro-level task with our proposed node-wise interaction alignment metrics; and Inductive Dynamic Graph Generation (IDGG), a macro-level task with our proposed metrics for aligning emergent network properties. On three real-world networks, Graphia improves micro-level alignment by 6.1% in the composite destination selection score, 12% in edge classification accuracy, and 27.9% in edge content BERTScore over the strongest baseline. For macro-level alignment, it achieves 35.98% higher structural similarity and 28.71% better replication of social phenomena such as power laws and echo chambers. Our results show that social graphs can serve as high-quality supervision signals for LLM post-training, closing the gap between agent behaviors and network dynamics for LLM-based simulation. Code is available at https://github.com/Ji-Cather/Graphia.git.

Ningyuan Chen, Setareh Farajollahzadeh, Guan Wang

Product bundling is a common selling mechanism used in online retailing. To set profitable bundle prices, the seller needs to learn consumer preferences from the transaction data. When customers purchase bundles or multiple products, classical methods such as discrete choice models cannot be used to estimate customers' valuations. In this paper, we propose an approach to learn the distribution of consumers' valuations toward the products using bundle sales data. The approach reduces it to an estimation problem where the samples are censored by polyhedral regions. Using the EM algorithm and Monte Carlo simulation, our approach can recover the distribution of consumers' valuations. The framework allows for unobserved no-purchases and clustered market segments. We provide theoretical results on the identifiability of the probability model and the convergence of the EM algorithm. The performance of the approach is also demonstrated numerically.

Hao Liu, Zhuoran Xu, Dan Wang et al.

3D object detection is a critical task in autonomous driving. Recently multi-modal fusion-based 3D object detection methods, which combine the complementary advantages of LiDAR and camera, have shown great performance improvements over mono-modal methods. However, so far, no methods have attempted to utilize the instance-level contextual image semantics to guide the 3D object detection. In this paper, we propose a simple and effective Painting Adaptive Instance-prior for 3D object detection (PAI3D) to fuse instance-level image semantics flexibly with point cloud features. PAI3D is a multi-modal sequential instance-level fusion framework. It first extracts instance-level semantic information from images, the extracted information, including objects categorical label, point-to-object membership and object position, are then used to augment each LiDAR point in the subsequent 3D detection network to guide and improve detection performance. PAI3D outperforms the state-of-the-art with a large margin on the nuScenes dataset, achieving 71.4 in mAP and 74.2 in NDS on the test split. Our comprehensive experiments show that instance-level image semantics contribute the most to the performance gain, and PAI3D works well with any good-quality instance segmentation models and any modern point cloud 3D encoders, making it a strong candidate for deployment on autonomous vehicles.

Guan Wang, Changling Liu, Chenyu Wang et al.

The current pretraining paradigm for large language models relies on massive compute and internet-scale raw text, creating a significant barrier to foundational research. In contrast, biological systems demonstrate highly sample-efficient learning through multi-timescale processing, such as the functional organization of the frontoparietal loop. Taking this as inspiration, we introduce HRM-Text, which replaces standard Transformers with a Hierarchical Recurrent Model (HRM) that decouples computation into slow-evolving strategic and fast-evolving execution layers. To stabilize this deep recurrence for language modeling, we introduce MagicNorm and warmup deep credit assignment. Furthermore, instead of standard raw-text pretraining, we train exclusively on instruction-response pairs using a task-completion objective and PrefixLM masking. Serving as an empirical existence proof of efficient pretraining, a 1B-parameter HRM-Text model trained from scratch on only 40 billion unique tokens and $1,500 budget achieves 60.7% on MMLU, 81.9% on ARC-C, 82.2% on DROP, 84.5% on GSM8K, and 56.2% on MATH. Despite utilizing roughly 100-900x fewer training tokens and 96-432x less estimated compute than standard baselines, HRM-Text performs competitively with 2-7B parameter open models. These results demonstrate that co-designing architectures and objectives can radically reduce the compute-to-performance ratio, making pretraining from scratch accessible to the broader research community.

Hengshuai Yao, Xing Chen, Ahmed Murtadha et al.

Standard transformer attention uses identical dimensionality for queries, keys, and values, yet these components serve different roles: queries and keys produce scalar attention weights (selection), while values carry rich representations (value transfer). We show that selection requires only $O(\log N)$ dimensions to distinguish among $N$ relevant token categories (e.g., syntactic roles, semantic clusters, positional patterns) -- far fewer than value transfer needs. We introduce factored keys, which exploit this asymmetry to physically shrink the KV cache of any pretrained model without retraining from scratch -- unlike GQA and MLA, which must be designed into the architecture before pretraining. We factorize each key projection $W_K \approx A_{d \times r} B_{r \times d}$ via truncated SVD (where $r = d_{\text{select}}$), set $W_K' = A$ as the new key projection producing compact $r$-dimensional keys for the cache, and absorb $B^\top$ into the query projection ($W_Q' = W_Q B^\top$) at zero cost -- since queries are never cached. At 7B scale, training from scratch with $r = d_{\text{model}}/4$ matches full-attention perplexity (9.2 vs 9.3 PPL after 20B tokens) while using 12% fewer parameters and training 8% faster. For existing models, SVD + QK fine-tuning (3 epochs, less than 1% of pretraining data) achieves 75% key cache savings at approximately 2% quality cost on both GPT-2 and Mistral-7B. The approach composes with GQA and quantization for up to $16\times$ combined key cache compression. For a 7B model serving 128K context, factored keys save 25 GB of KV cache per user, enabling approximately 60% more concurrent users on identical hardware.

Haoyang Cao, Xin Guo, Wenpin Tang et al.

Transfer learning is an essential technique for many machine learning/AI models of complex structures such as large language models and generative AI. The essence of transfer learning is to leverage knowledge from resolved source tasks for a new target task, especially when the sample size $m$ of the training data for the latter is low. In this work, we rigorously analyze the potential benefit of transfer learning in terms of sample efficiency. Specifically, taking an optimal transport viewpoint of transfer learning, we find that when the data dimension $d$ is higher than $3$, the sample complexity for transfer learning is $O(m^{-(α+1)/d})$, with $α$ indicating the smoothness of the data distribution, as opposed to the $O(m^{-p/d})$ sample complexity for direct learning with $p$ indicating the smoothness of the optimal target model. Our finding theoretically supports a better sample efficiency for transfer learning, when the target task is optimizing over a family of not-so-smooth models (i.e., highly complex networks with the possible use of non-smooth activation functions). Using image classification as an example, we numerically demonstrate the sample efficiency for transfer learning, that is, in the data hungry regime, the model performance can be significantly improved by transfer learning.

Shuai Shao, Yuhao Sun, Xing Chen et al.

Large-scale sparse multi-objective optimization problems (LSMOPs) are prevalent in real-world applications, where optimal solutions typically contain only a few nonzero variables, such as in adversarial attacks, critical node detection, and sparse signal reconstruction. Since the function evaluation of LSMOPs often relies on large-scale datasets involving a large number of decision variables, the search space becomes extremely high-dimensional. The coexistence of sparsity and high dimensionality greatly intensifies the conflict between exploration and exploitation, making it difficult for existing multi-objective evolutionary algorithms (MOEAs) to identify the critical nonzero decision variables within limited function evaluations. To address this challenge, this paper proposes an evolutionary algorithm with probabilistic annealing for large-scale sparse multi-objective optimization. The algorithm is driven by two probability vectors with distinct entropy characteristics: a convergence-oriented probability vector with relatively low entropy ensures stable exploitation, whereas an annealed probability vector with gradually decreasing entropy enables an adaptive transition from global exploration to local refinement. By integrating these complementary search dynamics, the proposed algorithm achieves a dynamic equilibrium between exploration and exploitation. Experimental results on benchmark problems and real-world applications demonstrate that the proposed algorithm outperforms state-of-the-art evolutionary algorithms in terms of both convergence and diversity.

Hengshuai Yao, Xing Chen, Ahmed Murtadha et al.

We introduce Focus, a method that learns which token pairs matter rather than approximating all of them. Learnable centroids assign tokens to groups; distant attention is restricted to same-group pairs while local attention operates at full resolution. Because all model weights stay frozen, Focus is purely additive: centroid-only training (as few as 148K parameters) improves domain perplexity with zero degradation on downstream benchmarks--from 124M to 70B parameters, across five attention architectures. No existing efficient attention method achieves this in the retrofit setting. At 124M, Focus surpasses full attention (30.3 vs 31.4 PPL); trained from scratch at 7B scale (2B tokens), Focus again beats full attention (13.82 vs 13.89 PPL). At inference, restricting each token to its top-k highest-scoring groups discretizes the soft routing into a hard sparsity pattern, yielding 2x speedup while beating the pretrained baseline (41.3 vs 42.8 PPL); decomposing this pattern into two standard FlashAttention calls reaches 8.6x wall-clock speedup at 1M tokens with no custom kernels. Unlike LoRA, centroid routing preserves alignment: instruction-tuned models retain TruthfulQA scores after adaptation, while LoRA degrades at every learning rate and rank. Sinkhorn normalization enforces balanced groups as a hard constraint, and the resulting groups discover interpretable linguistic categories without supervision.

Zhu Xu, Ting Lei, Zhimin Li et al.

Dynamic Scene Graph Generation (DSGG) aims to create a scene graph for each video frame by detecting objects and predicting their relationships. Weakly Supervised DSGG (WS-DSGG) reduces annotation workload by using an unlocalized scene graph from a single frame per video for training. Existing WS-DSGG methods depend on an off-the-shelf external object detector to generate pseudo labels for subsequent DSGG training. However, detectors trained on static, object-centric images struggle in dynamic, relation-aware scenarios required for DSGG, leading to inaccurate localization and low-confidence proposals. To address the challenges posed by external object detectors in WS-DSGG, we propose a Temporal-enhanced Relation-aware Knowledge Transferring (TRKT) method, which leverages knowledge to enhance detection in relation-aware dynamic scenarios. TRKT is built on two key components:(1)Relation-aware knowledge mining: we first employ object and relation class decoders that generate category-specific attention maps to highlight both object regions and interactive areas. Then we propose an Inter-frame Attention Augmentation strategy that exploits optical flow for neighboring frames to enhance the attention maps, making them motion-aware and robust to motion blur. This step yields relation- and motion-aware knowledge mining for WS-DSGG. (2) we introduce a Dual-stream Fusion Module that integrates category-specific attention maps into external detections to refine object localization and boost confidence scores for object proposals. Extensive experiments demonstrate that TRKT achieves state-of-the-art performance on Action Genome dataset. Our code is avaliable at https://github.com/XZPKU/TRKT.git.

Guan Wang, Weihua Li, Edmund Lai et al.

Text Summarization is recognised as one of the NLP downstream tasks and it has been extensively investigated in recent years. It can assist people with perceiving the information rapidly from the Internet, including news articles, social posts, videos, etc. Most existing research works attempt to develop summarization models to produce a better output. However, advent limitations of most existing models emerge, including unfaithfulness and factual errors. In this paper, we propose a novel model, named as Knowledge-aware Abstractive Text Summarization, which leverages the advantages offered by Knowledge Graph to enhance the standard Seq2Seq model. On top of that, the Knowledge Graph triplets are extracted from the source text and utilised to provide keywords with relational information, producing coherent and factually errorless summaries. We conduct extensive experiments by using real-world data sets. The results reveal that the proposed framework can effectively utilise the information from Knowledge Graph and significantly reduce the factual errors in the summary.

Michael Oliver, Guan Wang

This paper addresses the challenges of efficiently fine-tuning large language models (LLMs) by exploring data efficiency and hyperparameter optimization. We investigate the minimum data required for effective fine-tuning and propose a novel hyperparameter optimization method that leverages early-stage model performance. Our experiments demonstrate that fine-tuning with as few as 200 samples can improve model accuracy from 70\% to 88\% in a product attribute extraction task. We identify a saturation point of approximately 6,500 samples, beyond which additional data yields diminishing returns. Our proposed bayesian hyperparameter optimization method, which evaluates models at 20\% of total training time, correlates strongly with final model performance, with 4 out of 5 top early-stage models remaining in the top 5 at completion. This approach led to a 2\% improvement in accuracy over baseline models when evaluated on an independent test set. These findings offer actionable insights for practitioners, potentially reducing computational load and dependency on extensive datasets while enhancing overall performance of fine-tuned LLMs.

Guan Wang, Jin Li, Yuhao Sun et al.

Reasoning, the process of devising and executing complex goal-oriented action sequences, remains a critical challenge in AI. Current large language models (LLMs) primarily employ Chain-of-Thought (CoT) techniques, which suffer from brittle task decomposition, extensive data requirements, and high latency. Inspired by the hierarchical and multi-timescale processing in the human brain, we propose the Hierarchical Reasoning Model (HRM), a novel recurrent architecture that attains significant computational depth while maintaining both training stability and efficiency. HRM executes sequential reasoning tasks in a single forward pass without explicit supervision of the intermediate process, through two interdependent recurrent modules: a high-level module responsible for slow, abstract planning, and a low-level module handling rapid, detailed computations. With only 27 million parameters, HRM achieves exceptional performance on complex reasoning tasks using only 1000 training samples. The model operates without pre-training or CoT data, yet achieves nearly perfect performance on challenging tasks including complex Sudoku puzzles and optimal path finding in large mazes. Furthermore, HRM outperforms much larger models with significantly longer context windows on the Abstraction and Reasoning Corpus (ARC), a key benchmark for measuring artificial general intelligence capabilities. These results underscore HRM's potential as a transformative advancement toward universal computation and general-purpose reasoning systems.

Chao Xu, Yu Yang, Rongzhao Wang et al.

Multi-Stage Classifier (MSC) - several classifiers working sequentially in an arranged order and classification decision is partially made at each step - is widely used in industrial applications for various resource limitation reasons. The classifiers of a multi-stage process are usually Neural Network (NN) models trained independently or in their inference order without considering the signals from the latter stages. Aimed at two-stage binary classification process, the most common type of MSC, we propose a novel training framework, named Feedback Training. The classifiers are trained in an order reverse to their actual working order, and the classifier at the later stage is used to guide the training of initial-stage classifier via a sample weighting method. We experimentally show the efficacy of our proposed approach, and its great superiority under the scenario of few-shot training.

Yongrui Yu, Hanyu Chen, Zitian Zhang et al.

Despite the significant success achieved by deep learning methods in medical image segmentation, researchers still struggle in the computer-aided diagnosis of abdominal lymph nodes due to the complex abdominal environment, small and indistinguishable lesions, and limited annotated data. To address these problems, we present a pipeline that integrates the conditional diffusion model for lymph node generation and the nnU-Net model for lymph node segmentation to improve the segmentation performance of abdominal lymph nodes through synthesizing a diversity of realistic abdominal lymph node data. We propose LN-DDPM, a conditional denoising diffusion probabilistic model (DDPM) for lymph node (LN) generation. LN-DDPM utilizes lymph node masks and anatomical structure masks as model conditions. These conditions work in two conditioning mechanisms: global structure conditioning and local detail conditioning, to distinguish between lymph nodes and their surroundings and better capture lymph node characteristics. The obtained paired abdominal lymph node images and masks are used for the downstream segmentation task. Experimental results on the abdominal lymph node datasets demonstrate that LN-DDPM outperforms other generative methods in the abdominal lymph node image synthesis and better assists the downstream abdominal lymph node segmentation task.

Guan Wang, Rebecca Frederick, Jinglong Duan et al.

In this paper, we delve into the rapidly evolving challenge of misinformation detection, with a specific focus on the nuanced manipulation of narrative frames - an under-explored area within the AI community. The potential for Generative AI models to generate misleading narratives underscores the urgency of this problem. Drawing from communication and framing theories, we posit that the presentation or 'framing' of accurate information can dramatically alter its interpretation, potentially leading to misinformation. We highlight this issue through real-world examples, demonstrating how shifts in narrative frames can transmute fact-based information into misinformation. To tackle this challenge, we propose an innovative approach leveraging the power of pre-trained Large Language Models and deep neural networks to detect misinformation originating from accurate facts portrayed under different frames. These advanced AI techniques offer unprecedented capabilities in identifying complex patterns within unstructured data critical for examining the subtleties of narrative frames. The objective of this paper is to bridge a significant research gap in the AI domain, providing valuable insights and methodologies for tackling framing-induced misinformation, thus contributing to the advancement of responsible and trustworthy AI technologies. Several experiments are intensively conducted and experimental results explicitly demonstrate the various impact of elements of framing theory proving the rationale of applying framing theory to increase the performance in misinformation detection.

Hengshuai Yao, Xing Chen, Ahmed Murtadha et al.

Adapting LLMs to new domains causes forgetting because standard methods (full fine-tuning, LoRA) inject new directions into the weight space. We propose GAIN, which re-emphasizes existing features through multiplicative modulation W_new = S * W. The learned diagonal matrix S is applied to the attention output projection and optionally the FFN. The principle mirrors gain modulation in neuroscience, where neurons adapt to context by scaling response strength while preserving selectivity. We evaluate GAIN on five models from four families (774M to 70B), adapting sequentially across eight domains. GAIN-FFN matches LoRA's in-domain adaptation, but their effects on previously trained domains are opposite: GAIN-FFN improves them by 7-13% (validation PPL), while LoRA degrades them by 18-36%. Downstream accuracy confirms the pattern: for example, after seven sequential adaptations on Qwen2.5, GAIN-FFN degrades BoolQ by only 0.8% while LoRA damages it by 14.9%. GAIN adds 46K-230K parameters per model and can be absorbed into the pretrained weights for zero inference cost.

Shuyin Xia, Guan Wang, Gaojie Xu et al.

The objective of graph coarsening is to generate smaller, more manageable graphs while preserving key information of the original graph. Previous work were mainly based on the perspective of spectrum-preserving, using some predefined coarsening rules to make the eigenvalues of the Laplacian matrix of the original graph and the coarsened graph match as much as possible. However, they largely overlooked the fact that the original graph is composed of subregions at different levels of granularity, where highly connected and similar nodes should be more inclined to be aggregated together as nodes in the coarsened graph. By combining the multi-granularity characteristics of the graph structure, we can generate coarsened graph at the optimal granularity. To this end, inspired by the application of granular-ball computing in multi-granularity, we propose a new multi-granularity, efficient, and adaptive coarsening method via granular-ball (GBGC), which significantly improves the coarsening results and efficiency. Specifically, GBGC introduces an adaptive granular-ball graph refinement mechanism, which adaptively splits the original graph from coarse to fine into granular-balls of different sizes and optimal granularity, and constructs the coarsened graph using these granular-balls as supernodes. In addition, compared with other state-of-the-art graph coarsening methods, the processing speed of this method can be increased by tens to hundreds of times and has lower time complexity. The accuracy of GBGC is almost always higher than that of the original graph due to the good robustness and generalization of the granular-ball computing, so it has the potential to become a standard graph data preprocessing method.

Jie Peng, Rui Wang, Qiang Wang et al.

Information cascade popularity prediction is a key problem in analyzing content diffusion in social networks. However, current related works suffer from three critical limitations: (1) temporal leakage in current evaluation--random cascade-based splits allow models to access future information, yielding unrealistic results; (2) feature-poor datasets that lack downstream conversion signals (e.g., likes, comments, or purchases), which limits more practical applications; (3) computational inefficiency of complex graph-based methods that require days of training for marginal gains. We systematically address these challenges from three perspectives: task setup, dataset construction, and model design. First, we propose a time-ordered splitting strategy that chronologically partitions data into consecutive windows, ensuring models are evaluated on genuine forecasting tasks without future information leakage. Second, we introduce Taoke, a large-scale e-commerce cascade dataset featuring rich promoter/product attributes and ground-truth purchase conversions--capturing the complete diffusion lifecycle from promotion to monetization. Third, we develop CasTemp, a lightweight framework that efficiently models cascade dynamics through temporal walks, Jaccard-based neighbor selection for inter-cascade dependencies, and GRU-based encoding with time-aware attention. Under leak-free evaluation, CasTemp achieves state-of-the-art performance across four datasets with orders-of-magnitude speedup. Notably, it excels at predicting second-stage popularity conversions--a practical task critical for real-world applications.

Jiyan Qiu, Lyulin Kuang, Guan Wang et al.

Vehicle aerodynamics optimization has become critical for automotive electrification, where drag reduction directly determines electric vehicle range and energy efficiency. Traditional approaches face an intractable trade-off: computationally expensive Computational Fluid Dynamics (CFD) simulations requiring weeks per design iteration, or simplified models that sacrifice production-grade accuracy. While machine learning offers transformative potential, existing datasets exhibit fundamental limitations -- inadequate mesh resolution, missing vehicle components, and validation errors exceeding 5% -- preventing deployment in industrial workflows. We present DrivAerStar, comprising 12,000 industrial-grade automotive CFD simulations generated using STAR-CCM+${}^\unicode{xAE}$ software. The dataset systematically explores three vehicle configurations through 20 Computer Aided Design (CAD) parameters via Free Form Deformation (FFD) algorithms, including complete engine compartments and cooling systems with realistic internal airflow. DrivAerStar achieves wind tunnel validation accuracy below 1.04% -- a five-fold improvement over existing datasets -- through refined mesh strategies with strict wall $y^+$ control. Benchmarks demonstrate that models trained on this data achieve production-ready accuracy while reducing computational costs from weeks to minutes. This represents the first dataset bridging academic machine learning research and industrial CFD practice, establishing a new standard for data-driven aerodynamic optimization in automotive development. Beyond automotive applications, DrivAerStar demonstrates a paradigm for integrating high-fidelity physics simulations with Artificial Intelligence (AI) across engineering disciplines where computational constraints currently limit innovation.

Qi Li, Wendong Huang, Qichen Ye et al.

The E-commerce advertising platforms typically sell commercial traffic through either second-price auction (SPA) or first-price auction (FPA). SPA was historically prevalent due to its dominant strategy incentive-compatible (DSIC) for bidders with quasi-linear utilities, especially when budgets are not a binding constraint, while FPA has gained more prominence for offering higher revenue potential to publishers and avoiding the possibility for discriminatory treatment in personalized reserve prices. Meanwhile, on the demand side, advertisers are increasingly adopting platform-wide marketing solutions akin to QuanZhanTui, shifting from spending budgets solely on commercial traffic to bidding on the entire traffic for the purpose of maximizing overall sales. For automated bidding systems, such a trend poses a critical challenge: determining optimal strategies across heterogeneous auction channels to fulfill diverse advertiser objectives, such as maximizing return (MaxReturn) or meeting target return on ad spend (TargetROAS). To overcome this challenge, this work makes two key contributions. First, we derive an efficient solution for optimal bidding under FPA channels, which takes into account the presence of organic traffic - traffic can be won for free. Second, we introduce a marginal cost alignment (MCA) strategy that provably secures bidding efficiency across heterogeneous auction mechanisms. To validate performance of our developed framework, we conduct comprehensive offline experiments on public datasets and large-scale online A/B testing, which demonstrate consistent improvements over existing methods.

Enming Zhang, Zhengyu Li, Yanru Wu et al.

Recent advances in Vision Transformers (ViTs) have significantly advanced semantic segmentation performance. However, their adaptation to new target domains remains challenged by distribution shifts, which often disrupt global attention mechanisms. While existing global and patch-level adaptation methods offer some improvements, they overlook the spatially varying transferability inherent in different image regions. To address this, we propose the Transferable Mask Transformer (TMT), a region-adaptive framework designed to enhance cross-domain representation learning through transferability guidance. First, we dynamically partition the image into coherent regions, grouped by structural and semantic similarity, and estimates their domain transferability at a localized level. Then, we incorporate region-level transferability maps directly into the self-attention mechanism of ViTs, allowing the model to adaptively focus attention on areas with lower transferability and higher semantic uncertainty. Extensive experiments across 20 diverse cross-domain settings demonstrate that TMT not only mitigates the performance degradation typically associated with domain shift but also consistently outperforms existing approaches.

Guan Wang, Haoyi Niu, Jianxiong Li et al. · tsinghua

Among various branches of offline reinforcement learning (RL) methods, goal-conditioned supervised learning (GCSL) has gained increasing popularity as it formulates the offline RL problem as a sequential modeling task, therefore bypassing the notoriously difficult credit assignment challenge of value learning in conventional RL paradigm. Sequential modeling, however, requires capturing accurate dynamics across long horizons in trajectory data to ensure reasonable policy performance. To meet this requirement, leveraging large, expressive models has become a popular choice in recent literature, which, however, comes at the cost of significantly increased computation and inference latency. Contradictory yet promising, we reveal that lightweight models as simple as shallow 2-layer MLPs, can also enjoy accurate dynamics consistency and significantly reduced sequential modeling errors against large expressive models by adopting a simple recursive planning scheme: recursively planning coarse-grained future sub-goals based on current and target information, and then executes the action with a goal-conditioned policy learned from data rela-beled with these sub-goal ground truths. We term our method Recursive Skip-Step Planning (RSP). Simple yet effective, RSP enjoys great efficiency improvements thanks to its lightweight structure, and substantially outperforms existing methods, reaching new SOTA performances on the D4RL benchmark, especially in multi-stage long-horizon tasks.

Guan Wang, Weihua Li, Edmund M-K. Lai et al.

The rapid growth of information on the Internet has led to an overwhelming amount of opinions and comments on various activities, products, and services. This makes it difficult and time-consuming for users to process all the available information when making decisions. Text summarization, a Natural Language Processing (NLP) task, has been widely explored to help users quickly retrieve relevant information by generating short and salient content from long or multiple documents. Recent advances in pre-trained language models, such as ChatGPT, have demonstrated the potential of Large Language Models (LLMs) in text generation. However, LLMs require massive amounts of data and resources and are challenging to implement as offline applications. Furthermore, existing text summarization approaches often lack the ``adaptive" nature required to capture diverse aspects in opinion summarization, which is particularly detrimental to users with specific requirements or preferences. In this paper, we propose an Aspect-adaptive Knowledge-based Opinion Summarization model for product reviews, which effectively captures the adaptive nature required for opinion summarization. The model generates aspect-oriented summaries given a set of reviews for a particular product, efficiently providing users with useful information on specific aspects they are interested in, ensuring the generated summaries are more personalized and informative. Extensive experiments have been conducted using real-world datasets to evaluate the proposed model. The results demonstrate that our model outperforms state-of-the-art approaches and is adaptive and efficient in generating summaries that focus on particular aspects, enabling users to make well-informed decisions and catering to their diverse interests and preferences.

Zhitao Liu, Zengyu Liu, Jiwei Wei et al.

3D cross-modal retrieval is gaining attention in the multimedia community. Central to this topic is learning a joint embedding space to represent data from different modalities, such as images, 3D point clouds, and polygon meshes, to extract modality-invariant and discriminative features. Hence, the performance of cross-modal retrieval methods heavily depends on the representational capacity of this embedding space. Existing methods treat all instances equally, applying the same penalty strength to instances with varying degrees of difficulty, ignoring the differences between instances. This can result in ambiguous convergence or local optima, severely compromising the separability of the feature space. To address this limitation, we propose an Instance-Variant loss to assign different penalty strengths to different instances, improving the space separability. Specifically, we assign different penalty weights to instances positively related to their intra-class distance. Simultaneously, we reduce the cross-modal discrepancy between features by learning a shared weight vector for the same class data from different modalities. By leveraging the Gaussian RBF kernel to evaluate sample similarity, we further propose an Intra-Class loss function that minimizes the intra-class distance among same-class instances. Extensive experiments on three 3D cross-modal datasets show that our proposed method surpasses recent state-of-the-art approaches.

Haoyang Cao, Xin Guo, Guan Wang

Anomaly detection has been an active research area with a wide range of potential applications. Key challenges for anomaly detection in the AI era with big data include lack of prior knowledge of potential anomaly types, highly complex and noisy background in input data, scarce abnormal samples, and imbalanced training dataset. In this work, we propose a meta-learning framework for anomaly detection to deal with these issues. Within this framework, we incorporate the idea of generative adversarial networks (GANs) with appropriate choices of loss functions including structural similarity index measure (SSIM). Experiments with limited labeled data for high-speed rail inspection demonstrate that our meta-learning framework is sharp and robust in identifying anomalies. Our framework has been deployed in five high-speed railways of China since 2021: it has reduced more than 99.7% workload and saved 96.7% inspection time.

Guan Wang, Yusuke Kikuchi, Jinglin Yi et al.

Retinal vascular diseases affect the well-being of human body and sometimes provide vital signs of otherwise undetected bodily damage. Recently, deep learning techniques have been successfully applied for detection of diabetic retinopathy (DR). The main obstacle of applying deep learning techniques to detect most other retinal vascular diseases is the limited amount of data available. In this paper, we propose a transfer learning technique that aims to utilize the feature similarities for detecting retinal vascular diseases. We choose the well-studied DR detection as a source task and identify the early detection of retinopathy of prematurity (ROP) as the target task. Our experimental results demonstrate that our DR-pretrained approach dominates in all metrics the conventional ImageNet-pretrained transfer learning approach, currently adopted in medical image analysis. Moreover, our approach is more robust with respect to the stochasticity in the training process and with respect to reduced training samples. This study suggests the potential of our proposed transfer learning approach for a broad range of retinal vascular diseases or pathologies, where data is limited.

Guan Wang, Haoyi Niu, Desheng Zhu et al.

Heated debates continue over the best autonomous driving framework. The classic modular pipeline is widely adopted in the industry owing to its great interpretability and stability, whereas the fully end-to-end paradigm has demonstrated considerable simplicity and learnability along with the rise of deep learning. As a way of marrying the advantages of both approaches, learning a semantically meaningful representation and then use in the downstream driving policy learning tasks provides a viable and attractive solution. However, several key challenges remain to be addressed, including identifying the most effective representation, alleviating the sim-to-real generalization issue as well as balancing model training cost. In this study, we propose a versatile and efficient reinforcement learning framework and build a fully functional autonomous vehicle for real-world validation. Our framework shows great generalizability to various complicated real-world scenarios and superior training efficiency against the competing baselines.

Guan Wang, Hamid Laga, Anuj Srivastava

How can one analyze detailed 3D biological objects, such as neurons and botanical trees, that exhibit complex geometrical and topological variation? In this paper, we develop a novel mathematical framework for representing, comparing, and computing geodesic deformations between the shapes of such tree-like 3D objects. A hierarchical organization of subtrees characterizes these objects -- each subtree has the main branch with some side branches attached -- and one needs to match these structures across objects for meaningful comparisons. We propose a novel representation that extends the Square-Root Velocity Function (SRVF), initially developed for Euclidean curves, to tree-shaped 3D objects. We then define a new metric that quantifies the bending, stretching, and branch sliding needed to deform one tree-shaped object into the other. Compared to the current metrics, such as the Quotient Euclidean Distance (QED) and the Tree Edit Distance (TED), the proposed representation and metric capture the full elasticity of the branches (i.e., bending and stretching) as well as the topological variations (i.e., branch death/birth and sliding). It completely avoids the shrinkage that results from the edge collapse and node split operations of the QED and TED metrics. We demonstrate the utility of this framework in comparing, matching, and computing geodesics between biological objects such as neurons and botanical trees. The framework is also applied to various shape analysis tasks: (i) symmetry analysis and symmetrization of tree-shaped 3D objects, (ii) computing summary statistics (means and modes of variations) of populations of tree-shaped 3D objects, (iii) fitting parametric probability distributions to such populations, and (iv) finally synthesizing novel tree-shaped 3D objects through random sampling from estimated probability distributions.

Yuyang Zhang, Dik Hin Leung, Min Guo et al.

Matrix multiplication is the bedrock in Deep Learning inference application. When it comes to hardware acceleration on edge computing devices, matrix multiplication often takes up a great majority of the time. To achieve better performance in edge computing, we introduce a low-power Multi-layer Perceptron (MLP) accelerator based on a pipelined matrix multiplication scheme and a nonuniform quantization methodology. The implementation is running on Field-programmable Gate Array (FPGA) devices and tested its performance on handwritten digit classification and Q-learning tasks. Results show that our method can achieve better performance with fewer power consumption.

Guan Wang, Francois Bernard Lauze, Aasa Feragen

We present a graph neural network model for solving graph-to-graph learning problems. Most deep learning on graphs considers ``simple'' problems such as graph classification or regressing real-valued graph properties. For such tasks, the main requirement for intermediate representations of the data is to maintain the structure needed for output, i.e., keeping classes separated or maintaining the order indicated by the regressor. However, a number of learning tasks, such as regressing graph-valued output, generative models, or graph autoencoders, aim to predict a graph-structured output. In order to successfully do this, the learned representations need to preserve far more structure. We present a conditional auto-regressive model for graph-to-graph learning and illustrate its representational capabilities via experiments on challenging subgraph predictions from graph algorithmics; as a graph autoencoder for reconstruction and visualization; and on pretraining representations that allow graph classification with limited labeled data.

Jin Li, Jie Liu, Shangzhou Li et al.

Matching module plays a critical role in display advertising systems. Without query from user, it is challenging for system to match user traffic and ads suitably. System packs up a group of users with common properties such as the same gender or similar shopping interests into a crowd. Here term crowd can be viewed as a tag over users. Then advertisers bid for different crowds and deliver their ads to those targeted users. Matching module in most industrial display advertising systems follows a two-stage paradigm. When receiving a user request, matching system (i) finds the crowds that the user belongs to; (ii) retrieves all ads that have targeted those crowds. However, in applications such as display advertising at Alibaba, with very large volumes of crowds and ads, both stages of matching have to truncate the long-tailed parts for online serving, under limited latency. That's to say, not all ads have the chance to participate in online matching. This results in sub-optimal result for both advertising performance and platform revenue. In this paper, we study the truncation problem and propose a Truncation Free Matching System (TFMS). The basic idea is to decouple the matching computation from the online pipeline. Instead of executing the two-stage matching when user visits, TFMS utilizes a near-line truncation-free matching to pre-calculate and store those top valuable ads for each user. Then the online pipeline just needs to fetch the pre-stored ads as matching results. In this way, we can jump out of online system's latency and computation cost limitations, and leverage flexible computation resource to finish the user-ad matching. TFMS has been deployed in our productive system since 2019, bringing (i) more than 50% improvement of impressions for advertisers who encountered truncation before, (ii) 9.4% Revenue Per Mile gain, which is significant enough for the business.

Xiaotian Hao, Zhaoqing Peng, Yi Ma et al.

In E-commerce, advertising is essential for merchants to reach their target users. The typical objective is to maximize the advertiser's cumulative revenue over a period of time under a budget constraint. In real applications, an advertisement (ad) usually needs to be exposed to the same user multiple times until the user finally contributes revenue (e.g., places an order). However, existing advertising systems mainly focus on the immediate revenue with single ad exposures, ignoring the contribution of each exposure to the final conversion, thus usually falls into suboptimal solutions. In this paper, we formulate the sequential advertising strategy optimization as a dynamic knapsack problem. We propose a theoretically guaranteed bilevel optimization framework, which significantly reduces the solution space of the original optimization space while ensuring the solution quality. To improve the exploration efficiency of reinforcement learning, we also devise an effective action space reduction approach. Extensive offline and online experiments show the superior performance of our approaches over state-of-the-art baselines in terms of cumulative revenue.

Biye Jiang, Pengye Zhang, Rihan Chen et al.

Modern large-scale systems such as recommender system and online advertising system are built upon computation-intensive infrastructure. The typical objective in these applications is to maximize the total revenue, e.g. GMV~(Gross Merchandise Volume), under a limited computation resource. Usually, the online serving system follows a multi-stage cascade architecture, which consists of several stages including retrieval, pre-ranking, ranking, etc. These stages usually allocate resource manually with specific computing power budgets, which requires the serving configuration to adapt accordingly. As a result, the existing system easily falls into suboptimal solutions with respect to maximizing the total revenue. The limitation is due to the face that, although the value of traffic requests vary greatly, online serving system still spends equal computing power among them. In this paper, we introduce a novel idea that online serving system could treat each traffic request differently and allocate "personalized" computation resource based on its value. We formulate this resource allocation problem as a knapsack problem and propose a Dynamic Computation Allocation Framework~(DCAF). Under some general assumptions, DCAF can theoretically guarantee that the system can maximize the total revenue within given computation budget. DCAF brings significant improvement and has been deployed in the display advertising system of Taobao for serving the main traffic. With DCAF, we are able to maintain the same business performance with 20\% computation resource reduction.

Xin Guo, Yusuke Kikuchi, Guan Wang et al.

Retinopathy of prematurity (ROP) is an abnormal blood vessel development in the retina of a prematurely-born infant or an infant with low birth weight. ROP is one of the leading causes for infant blindness globally. Early detection of ROP is critical to slow down and avert the progression to vision impairment caused by ROP. Yet there is limited awareness of ROP even among medical professionals. Consequently, dataset for ROP is limited if ever available, and is in general extremely imbalanced in terms of the ratio between negative images and positive ones. In this study, we formulate the problem of detecting ROP in retinal fundus images in an optimization framework, and apply state-of-art convolutional neural network techniques to solve this problem. Experimental results based on our models achieve 100 percent sensitivity, 96 percent specificity, 98 percent accuracy, and 96 percent precision. In addition, our study shows that as the network gets deeper, more significant features can be extracted for better understanding of ROP.

Guan Wang, Charlie Xiaoqian Dang, Ziye Zhou

Federated Machine Learning (FML) creates an ecosystem for multiple parties to collaborate on building models while protecting data privacy for the participants. A measure of the contribution for each party in FML enables fair credits allocation. In this paper we develop simple but powerful techniques to fairly calculate the contributions of multiple parties in FML, in the context of both horizontal FML and vertical FML. For Horizontal FML we use deletion method to calculate the grouped instance influence. For Vertical FML we use Shapley Values to calculate the grouped feature importance. Our methods open the door for research in model contribution and credit allocation in the context of federated machine learning.

Yu Chen, Guan Wang

Pose estimation is a fundamental building block for robotic applications such as autonomous vehicles, UAV, and large scale augmented reality. It is also a prohibitive factor for those applications to be in mass production, since the state-of-the-art, centimeter-level pose estimation often requires long mapping procedures and expensive localization sensors, e.g. LiDAR and high precision GPS/IMU, etc. To overcome the cost barrier, we propose a neural network based solution to localize a consumer degree RGB camera within a prior sparse LiDAR map with comparable centimeter-level precision. We achieved it by introducing a novel network module, which we call resistor module, to enforce the network generalize better, predicts more accurately, and converge faster. Such results are benchmarked by several datasets we collected in the large scale indoor parking garage scenes. We plan to open both the data and the code for the community to join the effort to advance this field.

Guan Wang, Jianming Hu, Zhiheng Li et al.

In this paper, we study how to learn an appropriate lane changing strategy for autonomous vehicles by using deep reinforcement learning. We show that the reward of the system should consider the overall traffic efficiency instead of the travel efficiency of an individual vehicle. In summary, cooperation leads to a more harmonic and efficient traffic system rather than competition

Guan Wang

Federated Learning is introduced to protect privacy by distributing training data into multiple parties. Each party trains its own model and a meta-model is constructed from the sub models. In this way the details of the data are not disclosed in between each party. In this paper we investigate the model interpretation methods for Federated Learning, specifically on the measurement of feature importance of vertical Federated Learning where feature space of the data is divided into two parties, namely host and guest. For host party to interpret a single prediction of vertical Federated Learning model, the interpretation results, namely the feature importance, are very likely to reveal the protected data from guest party. We propose a method to balance the model interpretability and data privacy in vertical Federated Learning by using Shapley values to reveal detailed feature importance for host features and a unified importance value for federated guest features. Our experiments indicate robust and informative results for interpreting Federated Learning models.

Guan Wang, Fuming Ma, Yukun Guo et al.

This work is concerned with an inverse problem of identifying the current source distribution of the time-harmonic Maxwell's equations from multi-frequency measurements. Motivated by the Fourier method for the scalar Helmholtz equation and the polarization vector decomposition, we propose a novel method for determining the source function in the full vector Maxwell's system. Rigorous mathematical justifications of the method are given and numerical examples are provided to demonstrate the feasibility and effectiveness of the method.

James MacGlashan, Mark K Ho, Robert Loftin et al.

This paper investigates the problem of interactively learning behaviors communicated by a human teacher using positive and negative feedback. Much previous work on this problem has made the assumption that people provide feedback for decisions that is dependent on the behavior they are teaching and is independent from the learner's current policy. We present empirical results that show this assumption to be false -- whether human trainers give a positive or negative feedback for a decision is influenced by the learner's current policy. Based on this insight, we introduce {\em Convergent Actor-Critic by Humans} (COACH), an algorithm for learning from policy-dependent feedback that converges to a local optimum. Finally, we demonstrate that COACH can successfully learn multiple behaviors on a physical robot.

Qingbo Hu, Guan Wang, Philip S. Yu

Online video websites receive huge amount of videos daily from users all around the world. How to provide valuable recommendations to viewers is an important task for both video websites and related third parties, such as search engines. Previous work conducted numerous analysis on the view counts of videos, which measure a video's value in terms of popularity. However, the long-lasting value of an online video, namely longevity, is hidden behind the history that a video accumulates its "popularity" through time. Generally speaking, a longevous video tends to constantly draw society's attention. With focus on one of the leading video websites, Youtube, this paper proposes a scoring mechanism quantifying a video's longevity. Evaluating a video's longevity can not only improve a video recommender system, but also help us to discover videos having greater advertising value, as well as adjust a video website's strategy of storing videos to shorten its responding time. In order to accurately quantify longevity, we introduce the concept of latent social impulses and how to use them measure a video's longevity. In order to derive latent social impulses, we view the video website as a digital signal filter and formulate the task as a convex minimization problem. The proposed longevity computation is based on the derived social impulses. Unfortunately, the required information to derive social impulses are not always public, which makes a third party unable to directly evaluate every video's longevity. To solve this problem, we formulate a semi-supervised learning task by using part of videos having known longevity scores to predict the unknown longevity scores. We propose a Gaussian Random Markov model with Loopy Belief Propagation to solve this problem. The conducted experiments on Youtube demonstrate that the proposed method significantly improves the prediction results comparing to baselines.