EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions

GPT-4o, an omni-modal model that enables vocal conversations with diverse emotions and tones, marks a milestone for omni-modal foundation models. However, empowering Large Language Models to perceive and generate images, texts, and speeches end-to-end with publicly available data remains challenging in the open-source community. Existing vision-language models rely on external tools for the speech processing, while speech-language models still suffer from limited or even without vision-understanding abilities. To address this gap, we propose EMOVA (EMotionally Omni-present Voice Assistant), to enable Large Language Models with end-to-end speech capabilities while maintaining the leading vision-language performance. With a semantic-acoustic disentangled speech tokenizer, we notice surprisingly that omni-modal alignment can further enhance vision-language and speech abilities compared with the corresponding bi-modal aligned counterparts. Moreover, a lightweight style module is proposed for flexible speech style controls (e.g., emotions and pitches). For the first time, EMOVA achieves state-of-the-art performance on both the vision-language and speech benchmarks, and meanwhile, supporting omni-modal spoken dialogue with vivid emotions.

CoCA: Regaining Safety-awareness of Multimodal Large Language Models with Constitutional Calibration

The deployment of multimodal large language models (MLLMs) has demonstrated remarkable success in engaging in conversations involving visual inputs, thanks to the superior power of large language models (LLMs). Those MLLMs are typically built based on the LLMs, with an image encoder to process images into the token embedding space of the LLMs. However, the integration of visual modality has introduced a unique vulnerability: the MLLM becomes susceptible to malicious visual inputs and prone to generating sensitive or harmful responses, even though the LLM has been trained on textual dataset to align with human value. In this paper, we first raise the question: ``Do the MLLMs possess safety-awareness against malicious image inputs?". We find that after adding a principle that specifies the safety requirement into the input of the MLLM, the model's safety awareness becomes boosted. This phenomenon verifies the existence of MLLM's safety-awareness against image inputs, it is only weakened by the modality gap. We then introduce a simple yet effective technique termed CoCA, which amplifies the safety-awareness of the MLLM by calibrating its output distribution. Our proposed strategy helps the model reclaim its original safety awareness without losing its original capabilities. We verify the effectiveness of our approach on both multimodal safety and understanding benchmarks.

T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation

Text-to-video (T2V) generation models have advanced significantly, yet their ability to compose different objects, attributes, actions, and motions into a video remains unexplored. Previous text-to-video benchmarks also neglect this important ability for evaluation. In this work, we conduct the first systematic study on compositional text-to-video generation. We propose T2V-CompBench, the first benchmark tailored for compositional text-to-video generation. T2V-CompBench encompasses diverse aspects of compositionality, including consistent attribute binding, dynamic attribute binding, spatial relationships, motion binding, action binding, object interactions, and generative numeracy. We further carefully design evaluation metrics of MLLM-based metrics, detection-based metrics, and tracking-based metrics, which can better reflect the compositional text-to-video generation quality of seven proposed categories with 700 text prompts. The effectiveness of the proposed metrics is verified by correlation with human evaluations. We also benchmark various text-to-video generative models and conduct in-depth analysis across different models and different compositional categories. We find that compositional text-to-video generation is highly challenging for current models, and we hope that our attempt will shed light on future research in this direction.

GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing

Despite the success achieved by existing image generation and editing methods, current models still struggle with complex problems including intricate text prompts, and the absence of verification and self-correction mechanisms makes the generated images unreliable. Meanwhile, a single model tends to specialize in particular tasks and possess the corresponding capabilities, making it inadequate for fulfilling all user requirements. We propose GenArtist, a unified image generation and editing system, coordinated by a multimodal large language model (MLLM) agent. We integrate a comprehensive range of existing models into the tool library and utilize the agent for tool selection and execution. For a complex problem, the MLLM agent decomposes it into simpler sub-problems and constructs a tree structure to systematically plan the procedure of generation, editing, and self-correction with step-by-step verification. By automatically generating missing position-related inputs and incorporating position information, the appropriate tool can be effectively employed to address each sub-problem. Experiments demonstrate that GenArtist can perform various generation and editing tasks, achieving state-of-the-art performance and surpassing existing models such as SDXL and DALL-E 3, as can be seen in Fig. 1. Project page is https://zhenyuw16.github.io/GenArtist_page.

Jailbreaking as a Reward Misspecification Problem

The widespread adoption of large language models (LLMs) has raised concerns about their safety and reliability, particularly regarding their vulnerability to adversarial attacks. In this paper, we propose a novel perspective that attributes this vulnerability to reward misspecification during the alignment process. We introduce a metric ReGap to quantify the extent of reward misspecification and demonstrate its effectiveness and robustness in detecting harmful backdoor prompts. Building upon these insights, we present ReMiss, a system for automated red teaming that generates adversarial prompts against various target aligned LLMs. ReMiss achieves state-of-the-art attack success rates on the AdvBench benchmark while preserving the human readability of the generated prompts. Detailed analysis highlights the unique advantages brought by the proposed reward misspecification objective compared to previous methods.

QuickLLaMA: Query-aware Inference Acceleration for Large Language Models

The capacity of Large Language Models (LLMs) to comprehend and reason over long contexts is pivotal for advancements in diverse fields. Yet, they still stuggle with capturing long-distance dependencies within sequences to deeply understand semantics. To address this issue, we introduce Query-aware Inference for LLMs (Q-LLM), a system designed to process extensive sequences akin to human cognition. By focusing on memory data relevant to a given query, Q-LLM can accurately capture pertinent information within a fixed window size and provide precise answers to queries. It doesn't require extra training and can be seamlessly integrated with any LLMs. Q-LLM using LLaMA3 (QuickLLaMA) can read Harry Potter within 30s and accurately answer the questions. Q-LLM improved by 7.17% compared to the current state-of-the-art on LLaMA3, and by 3.26% on Mistral on the $\infty$-bench. In the Needle-in-a-Haystack task, On widely recognized benchmarks, Q-LLM improved upon the current SOTA by 7.0% on Mistral and achieves 100% on LLaMA3. Our code can be found in https://github.com/dvlab-research/Q-LLM.

Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data

Discrete diffusion models with absorbing processes have shown promise in language modeling. The key quantities to be estimated are the ratios between the marginal probabilities of two transitive states at all timesteps, called the concrete score. In this paper, we reveal that the concrete score in absorbing diffusion can be expressed as conditional probabilities of clean data, multiplied by a time-dependent scalar in an analytic form. Motivated by the finding, we propose reparameterized absorbing discrete diffusion (RADD), a dedicated diffusion model that characterizes the time-independent conditional probabilities. Besides its simplicity, RADD can reduce the number of function evaluations (NFEs) by caching the output of the time-independent network when the noisy sample remains unchanged in a sampling interval. Empirically, RADD is up to 3.5 times faster while consistently achieving a better performance than the strongest baseline. Built upon the new factorization of the concrete score, we further prove a surprising result that the exact likelihood of absorbing diffusion can be rewritten to a simple form (named denoising cross-entropy) and then estimated efficiently by the Monte Carlo method. The resulting approach also applies to the original parameterization of the concrete score. It significantly advances the state-of-the-art discrete diffusion on 5 zero-shot language modeling benchmarks (measured by perplexity) at the GPT-2 scale.

Enhancing Text-to-Image Editing via Hybrid Mask-Informed Fusion

Recently, text-to-image (T2I) editing has been greatly pushed forward by applying diffusion models. Despite the visual promise of the generated images, inconsistencies with the expected textual prompt remain prevalent. This paper aims to systematically improve the text-guided image editing techniques based on diffusion models, by addressing their limitations. Notably, the common idea in diffusion-based editing firstly reconstructs the source image via inversion techniques e.g., DDIM Inversion. Then following a fusion process that carefully integrates the source intermediate (hidden) states (obtained by inversion) with the ones of the target image. Unfortunately, such a standard pipeline fails in many cases due to the interference of texture retention and the new characters creation in some regions. To mitigate this, we incorporate human annotation as an external knowledge to confine editing within a ``Mask-informed'' region. Then we carefully Fuse the edited image with the source image and a constructed intermediate image within the model's Self-Attention module. Extensive empirical results demonstrate the proposed ``MaSaFusion'' significantly improves the existing T2I editing techniques.

Towards Understanding the Working Mechanism of Text-to-Image Diffusion Model

Recently, the strong latent Diffusion Probabilistic Model (DPM) has been applied to high-quality Text-to-Image (T2I) generation (e.g., Stable Diffusion), by injecting the encoded target text prompt into the gradually denoised diffusion image generator. Despite the success of DPM in practice, the mechanism behind it remains to be explored. To fill this blank, we begin by examining the intermediate statuses during the gradual denoising generation process in DPM. The empirical observations indicate, the shape of image is reconstructed after the first few denoising steps, and then the image is filled with details (e.g., texture). The phenomenon is because the low-frequency signal (shape relevant) of the noisy image is not corrupted until the final stage in the forward process (initial stage of generation) of adding noise in DPM. Inspired by the observations, we proceed to explore the influence of each token in the text prompt during the two stages. After a series of experiments of T2I generations conditioned on a set of text prompts. We conclude that in the earlier generation stage, the image is mostly decided by the special token [\texttt{EOS}] in the text prompt, and the information in the text prompt is already conveyed in this stage. After that, the diffusion model completes the details of generated images by information from themselves. Finally, we propose to apply this observation to accelerate the process of T2I generation by properly removing text guidance, which finally accelerates the sampling up to 25\%+.

Towards Understanding How Transformer Perform Multi-step Reasoning with Matching Operation

Large language models have consistently struggled with complex reasoning tasks, such as mathematical problem-solving. Investigating the internal reasoning mechanisms of these models can help us design better model architectures and training strategies, ultimately enhancing their reasoning capabilities. In this study, we examine the matching mechanism employed by Transformer for multi-step reasoning on a constructed dataset. We investigate factors that influence the model's matching mechanism and discover that small initialization and post-LayerNorm can facilitate the formation of the matching mechanism, thereby enhancing the model's reasoning ability. Moreover, we propose a method to improve the model's reasoning capability by adding orthogonal noise. Finally, we investigate the parallel reasoning mechanism of Transformers and propose a conjecture on the upper bound of the model's reasoning ability based on this phenomenon. These insights contribute to a deeper understanding of the reasoning processes in large language models and guide designing more effective reasoning architectures and training strategies.