Haoran Tang

Ruyang Liu, Chen Li, Haoran Tang et al. · tencent-ai

Large Language Models (LLMs) have showcased impressive capabilities in text comprehension and generation, prompting research efforts towards video LLMs to facilitate human-AI interaction at the video level. However, how to effectively encode and understand videos in video-based dialogue systems remains to be solved. In this paper, we investigate a straightforward yet unexplored question: Can we feed all spatial-temporal tokens into the LLM, thus delegating the task of video sequence modeling to the LLMs? Surprisingly, this simple approach yields significant improvements in video understanding. Based upon this, we propose ST-LLM, an effective video-LLM baseline with Spatial-Temporal sequence modeling inside LLM. Furthermore, to address the overhead and stability issues introduced by uncompressed video tokens within LLMs, we develop a dynamic masking strategy with tailor-made training objectives. For particularly long videos, we have also designed a global-local input module to balance efficiency and effectiveness. Consequently, we harness LLM for proficient spatial-temporal modeling, while upholding efficiency and stability. Extensive experimental results attest to the effectiveness of our method. Through a more concise model and training pipeline, ST-LLM establishes a new state-of-the-art result on VideoChatGPT-Bench and MVBench. Codes have been available at https://github.com/TencentARC/ST-LLM.

Zixuan Wang, Haoran Tang, Haibo Wang et al.

Despite the remarkable results that can be achieved by data-driven intelligent fault diagnosis techniques, they presuppose the same distribution of training and test data as well as sufficient labeled data. Various operating states often exist in practical scenarios, leading to the problem of domain shift that hinders the effectiveness of fault diagnosis. While recent unsupervised domain adaptation methods enable cross-domain fault diagnosis, they struggle to effectively utilize information from multiple source domains and achieve effective diagnosis faults in multiple target domains simultaneously. In this paper, we innovatively proposed a weighted joint maximum mean discrepancy enabled multi-source-multi-target unsupervised domain adaptation (WJMMD-MDA), which realizes domain adaptation under multi-source-multi-target scenarios in the field of fault diagnosis for the first time. The proposed method extracts sufficient information from multiple labeled source domains and achieves domain alignment between source and target domains through an improved weighted distance loss. As a result, domain-invariant and discriminative features between multiple source and target domains are learned with cross-domain fault diagnosis realized. The performance of the proposed method is evaluated in comprehensive comparative experiments on three datasets, and the experimental results demonstrate the superiority of this method.

Ruyang Liu, Haoran Tang, Haibo Liu et al. · tencent-ai

The past year has witnessed the significant advancement of video-based large language models. However, the challenge of developing a unified model for both short and long video understanding remains unresolved. Most existing video LLMs cannot handle hour-long videos, while methods custom for long videos tend to be ineffective for shorter videos and images. In this paper, we identify the key issue as the redundant content in videos. To address this, we propose a novel pooling strategy that simultaneously achieves token compression and instruction-aware visual feature aggregation. Our model is termed Prompt-guided Pooling LLaVA, or PPLLaVA for short. Specifically, PPLLaVA consists of three core components: the CLIP-based visual-prompt alignment that extracts visual information relevant to the user's instructions, the prompt-guided pooling that compresses the visual sequence to arbitrary scales using convolution-style pooling, and the clip context extension designed for lengthy prompt common in visual dialogue. Moreover, our codebase also integrates the most advanced video Direct Preference Optimization (DPO) and visual interleave training. Extensive experiments have validated the performance of our model. With superior throughput and only 1024 visual context, PPLLaVA achieves better results on image benchmarks as a video LLM, while achieving state-of-the-art performance across various video benchmarks, excelling in tasks ranging from caption generation to multiple-choice questions, and handling video lengths from seconds to hours. Codes have been available at https://github.com/farewellthree/PPLLaVA.

Xiang Li, Haoran Tang, Siyu Chen et al.

We measure the performance of in-context learning as a function of task novelty and difficulty for open and closed questions. For that purpose, we created a novel benchmark consisting of hard scientific questions, each paired with a context of various relevancy. We show that counter-intuitively, a context that is more aligned with the topic does not always help more than a less relevant context. This effect is especially visible for open questions and questions of high difficulty or novelty. This result reveals a fundamental difference between the treatment of close-form and open-form questions by large-language models and shows a need for a more robust evaluation of in-context learning on the variety of different types of questions. It also poses a new question of how to optimally select a context for large language models, especially in the context of Retrieval Augmented Generation (RAG) systems. Our results suggest that the answer to this question can be highly application-dependent and might be contingent on factors including the format of the question, the perceived difficulty level of the questions, and the novelty or popularity of the information we seek.

Haoran Tang, Jieren Deng, Zhihong Pan et al.

Diffusion-based methods have demonstrated remarkable capabilities in generating a diverse array of high-quality images, sparking interests for styled avatars, virtual try-on, and more. Previous methods use the same reference image as the target. An overlooked aspect is the leakage of the target's spatial information, style, etc. from the reference, harming the generated diversity and causing shortcuts. However, this approach continues as widely available datasets usually consist of single images not grouped by identities, and it is expensive to recollect large-scale same-identity data. Moreover, existing metrics adopt decoupled evaluation on text alignment and identity preservation, which fail at distinguishing between balanced outputs and those that over-fit to one aspect. In this paper, we propose a multi-level, same-identity dataset RetriBooru, which groups anime characters by both face and cloth identities. RetriBooru enables adopting reference images of the same character and outfits as the target, while keeping flexible gestures and actions. We benchmark previous methods on our dataset, and demonstrate the effectiveness of training with a reference image different from target (but same identity). We introduce a new concept composition task, where the conditioning encoder learns to retrieve different concepts from several reference images, and modify a baseline network RetriNet for the new task. Finally, we introduce a novel class of metrics named Similarity Weighted Diversity (SWD), to measure the overlooked diversity and better evaluate the alignment between similarity and diversity.

Yicong Li, Yu Yang, Jiannong Cao et al.

Recent studies successfully learned static graph embeddings that are structurally fair by preventing the effectiveness disparity of high- and low-degree vertex groups in downstream graph mining tasks. However, achieving structure fairness in dynamic graph embedding remains an open problem. Neglecting degree changes in dynamic graphs will significantly impair embedding effectiveness without notably improving structure fairness. This is because the embedding performance of high-degree and low-to-high-degree vertices will significantly drop close to the generally poorer embedding performance of most slightly changed vertices in the long-tail part of the power-law distribution. We first identify biased structural evolutions in a dynamic graph based on the evolving trend of vertex degree and then propose FairDGE, the first structurally Fair Dynamic Graph Embedding algorithm. FairDGE learns biased structural evolutions by jointly embedding the connection changes among vertices and the long-short-term evolutionary trend of vertex degrees. Furthermore, a novel dual debiasing approach is devised to encode fair embeddings contrastively, customizing debiasing strategies for different biased structural evolutions. This innovative debiasing strategy breaks the effectiveness bottleneck of embeddings without notable fairness loss. Extensive experiments demonstrate that FairDGE achieves simultaneous improvement in the effectiveness and fairness of embeddings.

Xiang Li, Haoran Tang, Siyu Chen et al.

In this paper, we explore the challenges inherent to Large Language Models (LLMs) like GPT-4, particularly their propensity for hallucinations, logic mistakes, and incorrect conclusions when tasked with answering complex questions. The capacity of LLMs to present erroneous answers in a coherent and semantically rigorous manner further complicates the detection of factual inaccuracies. This issue is especially pronounced in fields that require specialized expertise. Our work delves into these challenges, aiming to enhance the understanding and mitigation of such errors, thereby contributing to the improvement of LLM accuracy and reliability in scientific and other specialized domains. Our findings reveal a non-linear relationship between the context's relevancy and the answers' measured quality. In addition, we demonstrate that with the correct calibration, it is possible to automate the grading procedure -- a finding suggesting that, at least to some degree, the LLMs can be used to self-examine the quality of their own performance. Finally, we describe an experimental platform that can be seen as a proof-of-concept of the techniques described in this work.

Ofir Nachum, Haoran Tang, Xingyu Lu et al.

Hierarchical reinforcement learning has demonstrated significant success at solving difficult reinforcement learning (RL) tasks. Previous works have motivated the use of hierarchy by appealing to a number of intuitive benefits, including learning over temporally extended transitions, exploring over temporally extended periods, and training and exploring in a more semantically meaningful action space, among others. However, in fully observed, Markovian settings, it is not immediately clear why hierarchical RL should provide benefits over standard "shallow" RL architectures. In this work, we isolate and evaluate the claimed benefits of hierarchical RL on a suite of tasks encompassing locomotion, navigation, and manipulation. Surprisingly, we find that most of the observed benefits of hierarchy can be attributed to improved exploration, as opposed to easier policy learning or imposed hierarchical structures. Given this insight, we present exploration techniques inspired by hierarchy that achieve performance competitive with hierarchical RL while at the same time being much simpler to use and implement.

Dennis Lee, Haoran Tang, Jeffrey O Zhang et al.

We present a novel modular architecture for StarCraft II AI. The architecture splits responsibilities between multiple modules that each control one aspect of the game, such as build-order selection or tactics. A centralized scheduler reviews macros suggested by all modules and decides their order of execution. An updater keeps track of environment changes and instantiates macros into series of executable actions. Modules in this framework can be optimized independently or jointly via human design, planning, or reinforcement learning. We apply deep reinforcement learning techniques to training two out of six modules of a modular agent with self-play, achieving 94% or 87% win rates against the "Harder" (level 5) built-in Blizzard bot in Zerg vs. Zerg matches, with or without fog-of-war.

Tuomas Haarnoja, Haoran Tang, Pieter Abbeel et al.

We propose a method for learning expressive energy-based policies for continuous states and actions, which has been feasible only in tabular domains before. We apply our method to learning maximum entropy policies, resulting into a new algorithm, called soft Q-learning, that expresses the optimal policy via a Boltzmann distribution. We use the recently proposed amortized Stein variational gradient descent to learn a stochastic sampling network that approximates samples from this distribution. The benefits of the proposed algorithm include improved exploration and compositionality that allows transferring skills between tasks, which we confirm in simulated experiments with swimming and walking robots. We also draw a connection to actor-critic methods, which can be viewed performing approximate inference on the corresponding energy-based model.

Haoran Tang, Rein Houthooft, Davis Foote et al.

Count-based exploration algorithms are known to perform near-optimally when used in conjunction with tabular reinforcement learning (RL) methods for solving small discrete Markov decision processes (MDPs). It is generally thought that count-based methods cannot be applied in high-dimensional state spaces, since most states will only occur once. Recent deep RL exploration strategies are able to deal with high-dimensional continuous state spaces through complex heuristics, often relying on optimism in the face of uncertainty or intrinsic motivation. In this work, we describe a surprising finding: a simple generalization of the classic count-based approach can reach near state-of-the-art performance on various high-dimensional and/or continuous deep RL benchmarks. States are mapped to hash codes, which allows to count their occurrences with a hash table. These counts are then used to compute a reward bonus according to the classic count-based exploration theory. We find that simple hash functions can achieve surprisingly good results on many challenging tasks. Furthermore, we show that a domain-dependent learned hash code may further improve these results. Detailed analysis reveals important aspects of a good hash function: 1) having appropriate granularity and 2) encoding information relevant to solving the MDP. This exploration strategy achieves near state-of-the-art performance on both continuous control tasks and Atari 2600 games, hence providing a simple yet powerful baseline for solving MDPs that require considerable exploration.