Falcon: A Remote Sensing Vision-Language Foundation Model

This paper introduces a holistic vision-language foundation model tailored for remote sensing, named Falcon. Falcon offers a unified, prompt-based paradigm that effectively executes comprehensive and complex remote sensing tasks. Falcon demonstrates powerful understanding and reasoning abilities at the image, region, and pixel levels. Specifically, given simple natural language instructions and remote sensing images, Falcon can produce impressive results in text form across 14 distinct tasks, i.e., image classification, object detection, segmentation, image captioning, and etc. To facilitate Falcon's training and empower its representation capacity to encode rich spatial and semantic information, we developed Falcon_SFT, a large-scale, multi-task, instruction-tuning dataset in the field of remote sensing. The Falcon_SFT dataset consists of approximately 78 million high-quality data samples, covering 5.6 million multi-spatial resolution and multi-view remote sensing images with diverse instructions. It features hierarchical annotations and undergoes manual sampling verification to ensure high data quality and reliability. Extensive comparative experiments are conducted, which verify that Falcon achieves remarkable performance over 67 datasets and 14 tasks, despite having only 0.7B parameters. We release the complete dataset, code, and model weights at https://github.com/TianHuiLab/Falcon, hoping to help further develop the open-source community.

Beyond Overfitting: Doubly Adaptive Dropout for Generalizable AU Detection

Facial Action Units (AUs) are essential for conveying psychological states and emotional expressions. While automatic AU detection systems leveraging deep learning have progressed, they often overfit to specific datasets and individual features, limiting their cross-domain applicability. To overcome these limitations, we propose a doubly adaptive dropout approach for cross-domain AU detection, which enhances the robustness of convolutional feature maps and spatial tokens against domain shifts. This approach includes a Channel Drop Unit (CD-Unit) and a Token Drop Unit (TD-Unit), which work together to reduce domain-specific noise at both the channel and token levels. The CD-Unit preserves domain-agnostic local patterns in feature maps, while the TD-Unit helps the model identify AU relationships generalizable across domains. An auxiliary domain classifier, integrated at each layer, guides the selective omission of domain-sensitive features. To prevent excessive feature dropout, a progressive training strategy is used, allowing for selective exclusion of sensitive features at any model layer. Our method consistently outperforms existing techniques in cross-domain AU detection, as demonstrated by extensive experimental evaluations. Visualizations of attention maps also highlight clear and meaningful patterns related to both individual and combined AUs, further validating the approach's effectiveness.

Parametric Value Approximation for General-sum Differential Games with State Constraints

General-sum differential games can approximate values solved by Hamilton-Jacobi-Isaacs (HJI) equations for efficient inference when information is incomplete. However, solving such games through conventional methods encounters the curse of dimensionality (CoD). Physics-informed neural networks (PINNs) offer a scalable approach to alleviate the CoD and approximate values, but there exist convergence issues for value approximations through vanilla PINNs when state constraints lead to values with large Lipschitz constants, particularly in safety-critical applications. In addition to addressing CoD, it is necessary to learn a generalizable value across a parametric space of games, rather than training multiple ones for each specific player-type configuration. To overcome these challenges, we propose a Hybrid Neural Operator (HNO), which is an operator that can map parameter functions for games to value functions. HNO leverages informative supervised data and samples PDE-driven data across entire spatial-temporal space for model refinement. We evaluate HNO on 9D and 13D scenarios with nonlinear dynamics and state constraints, comparing it against a Supervised Neural Operator (a variant of DeepONet). Under the same computational budget and training data, HNO outperforms SNO for safety performance. This work provides a step toward scalable and generalizable value function approximation, enabling real-time inference for complex human-robot or multi-agent interactions.

Learning Nash Equilibrial Hamiltonian for Two-Player Collision-Avoiding Interactions

We consider the problem of learning Nash equilibrial policies for two-player risk-sensitive collision-avoiding interactions. Solving the Hamilton-Jacobi-Isaacs equations of such general-sum differential games in real time is an open challenge due to the discontinuity of equilibrium values on the state space. A common solution is to learn a neural network that approximates the equilibrium Hamiltonian for given system states and actions. The learning, however, is usually supervised and requires a large amount of sample equilibrium policies from different initial states in order to mitigate the risks of collisions. This paper claims two contributions towards more data-efficient learning of equilibrium policies: First, instead of computing Hamiltonian through a value network, we show that the equilibrium co-states have simple structures when collision avoidance dominates the agents' loss functions and system dynamics is linear, and therefore are more data-efficient to learn. Second, we introduce theory-driven active learning to guide data sampling, where the acquisition function measures the compliance of the predicted co-states to Pontryagin's Maximum Principle. On an uncontrolled intersection case, the proposed method leads to more generalizable approximation of the equilibrium policies, and in turn, lower collision probabilities, than the state-of-the-art under the same data acquisition budget.

Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis

While recent zero-shot text-to-speech (TTS) models have significantly improved speech quality and expressiveness, mainstream systems still suffer from issues related to speech-text alignment modeling: 1) models without explicit speech-text alignment modeling exhibit less robustness, especially for hard sentences in practical applications; 2) predefined alignment-based models suffer from naturalness constraints of forced alignments. This paper introduces \textit{S-DiT}, a TTS system featuring an innovative sparse alignment algorithm that guides the latent diffusion transformer (DiT). Specifically, we provide sparse alignment boundaries to S-DiT to reduce the difficulty of alignment learning without limiting the search space, thereby achieving high naturalness. Moreover, we employ a multi-condition classifier-free guidance strategy for accent intensity adjustment and adopt the piecewise rectified flow technique to accelerate the generation process. Experiments demonstrate that S-DiT achieves state-of-the-art zero-shot TTS speech quality and supports highly flexible control over accent intensity. Notably, our system can generate high-quality one-minute speech with only 8 sampling steps. Audio samples are available at https://sditdemo.github.io/sditdemo/.

HumanDiT: Pose-Guided Diffusion Transformer for Long-form Human Motion Video Generation

Human motion video generation has advanced significantly, while existing methods still struggle with accurately rendering detailed body parts like hands and faces, especially in long sequences and intricate motions. Current approaches also rely on fixed resolution and struggle to maintain visual consistency. To address these limitations, we propose HumanDiT, a pose-guided Diffusion Transformer (DiT)-based framework trained on a large and wild dataset containing 14,000 hours of high-quality video to produce high-fidelity videos with fine-grained body rendering. Specifically, (i) HumanDiT, built on DiT, supports numerous video resolutions and variable sequence lengths, facilitating learning for long-sequence video generation; (ii) we introduce a prefix-latent reference strategy to maintain personalized characteristics across extended sequences. Furthermore, during inference, HumanDiT leverages Keypoint-DiT to generate subsequent pose sequences, facilitating video continuation from static images or existing videos. It also utilizes a Pose Adapter to enable pose transfer with given sequences. Extensive experiments demonstrate its superior performance in generating long-form, pose-accurate videos across diverse scenarios.

FAMES: Fast Approximate Multiplier Substitution for Mixed-Precision Quantized DNNs--Down to 2 Bits!

A widely-used technique in designing energy-efficient deep neural network (DNN) accelerators is quantization. Recent progress in this direction has reduced the bitwidths used in DNN down to 2. Meanwhile, many prior works apply approximate multipliers (AppMuls) in designing DNN accelerators to lower their energy consumption. Unfortunately, these works still assume a bitwidth much larger than 2, which falls far behind the state-of-the-art in quantization area and even challenges the meaningfulness of applying AppMuls in DNN accelerators, since a high-bitwidth AppMul consumes much more energy than a low-bitwidth exact multiplier! Thus, an important problem to study is: Can approximate multipliers be effectively applied to quantized DNN models with very low bitwidths? In this work, we give an affirmative answer to this question and present a systematic solution that achieves the answer: FAMES, a fast approximate multiplier substitution method for mixed-precision DNNs. Our experiments demonstrate an average 28.67% energy reduction on state-of-the-art mixed-precision quantized models with bitwidths as low as 2 bits and accuracy losses kept under 1%. Additionally, our approach is up to 300x faster than previous genetic algorithm-based methods.

Sharingan: Extract User Action Sequence from Desktop Recordings

Video recordings of user activities, particularly desktop recordings, offer a rich source of data for understanding user behaviors and automating processes. However, despite advancements in Vision-Language Models (VLMs) and their increasing use in video analysis, extracting user actions from desktop recordings remains an underexplored area. This paper addresses this gap by proposing two novel VLM-based methods for user action extraction: the Direct Frame-Based Approach (DF), which inputs sampled frames directly into VLMs, and the Differential Frame-Based Approach (DiffF), which incorporates explicit frame differences detected via computer vision techniques. We evaluate these methods using a basic self-curated dataset and an advanced benchmark adapted from prior work. Our results show that the DF approach achieves an accuracy of 70% to 80% in identifying user actions, with the extracted action sequences being re-playable though Robotic Process Automation. We find that while VLMs show potential, incorporating explicit UI changes can degrade performance, making the DF approach more reliable. This work represents the first application of VLMs for extracting user action sequences from desktop recordings, contributing new methods, benchmarks, and insights for future research.

MMCS: A Multimodal Medical Diagnosis System Integrating Image Analysis and Knowledge-based Departmental Consultation

We present MMCS, a system capable of recognizing medical images and patient facial details, and providing professional medical diagnoses. The system consists of two core components: The first component is the analysis of medical images and videos. We trained a specialized multimodal medical model capable of interpreting medical images and accurately analyzing patients' facial emotions and facial paralysis conditions. The model achieved an accuracy of 72.59% on the FER2013 facial emotion recognition dataset, with a 91.1% accuracy in recognizing the happy emotion. In facial paralysis recognition, the model reached an accuracy of 92%, which is 30% higher than that of GPT-4o. Based on this model, we developed a parser for analyzing facial movement videos of patients with facial paralysis, achieving precise grading of the paralysis severity. In tests on 30 videos of facial paralysis patients, the system demonstrated a grading accuracy of 83.3%.The second component is the generation of professional medical responses. We employed a large language model, integrated with a medical knowledge base, to generate professional diagnoses based on the analysis of medical images or videos. The core innovation lies in our development of a department-specific knowledge base routing management mechanism, in which the large language model categorizes data by medical departments and, during the retrieval process, determines the appropriate knowledge base to query. This significantly improves retrieval accuracy in the RAG (retrieval-augmented generation) process. This mechanism led to an average increase of 4 percentage points in accuracy for various large language models on the MedQA dataset.Our code is open-sourced and available at: https://github.com/renllll/MMCS.

MimicTalk: Mimicking a personalized and expressive 3D talking face in minutes

Talking face generation (TFG) aims to animate a target identity's face to create realistic talking videos. Personalized TFG is a variant that emphasizes the perceptual identity similarity of the synthesized result (from the perspective of appearance and talking style). While previous works typically solve this problem by learning an individual neural radiance field (NeRF) for each identity to implicitly store its static and dynamic information, we find it inefficient and non-generalized due to the per-identity-per-training framework and the limited training data. To this end, we propose MimicTalk, the first attempt that exploits the rich knowledge from a NeRF-based person-agnostic generic model for improving the efficiency and robustness of personalized TFG. To be specific, (1) we first come up with a person-agnostic 3D TFG model as the base model and propose to adapt it into a specific identity; (2) we propose a static-dynamic-hybrid adaptation pipeline to help the model learn the personalized static appearance and facial dynamic features; (3) To generate the facial motion of the personalized talking style, we propose an in-context stylized audio-to-motion model that mimics the implicit talking style provided in the reference video without information loss by an explicit style representation. The adaptation process to an unseen identity can be performed in 15 minutes, which is 47 times faster than previous person-dependent methods. Experiments show that our MimicTalk surpasses previous baselines regarding video quality, efficiency, and expressiveness. Source code and video samples are available at https://mimictalk.github.io .