The Devil is in the Distributions: Explicit Modeling of Scene Content is Key in Zero-Shot Video Captioning

Zero-shot video captioning requires that a model generate high-quality captions without human-annotated video-text pairs for training. State-of-the-art approaches to the problem leverage CLIP to extract visual-relevant textual prompts to guide language models in generating captions. These methods tend to focus on one key aspect of the scene and build a caption that ignores the rest of the visual input. To address this issue, and generate more accurate and complete captions, we propose a novel progressive multi-granularity textual prompting strategy for zero-shot video captioning. Our approach constructs three distinct memory banks, encompassing noun phrases, scene graphs of noun phrases, and entire sentences. Moreover, we introduce a category-aware retrieval mechanism that models the distribution of natural language surrounding the specific topics in question. Extensive experiments demonstrate the effectiveness of our method with 5.7%, 16.2%, and 3.4% improvements in terms of the main metric CIDEr on MSR-VTT, MSVD, and VATEX benchmarks compared to existing state-of-the-art.

MATHGLANCE: Multimodal Large Language Models Do Not Know Where to Look in Mathematical Diagrams

Diagrams serve as a fundamental form of visual language, representing complex concepts and their inter-relationships through structured symbols, shapes, and spatial arrangements. Unlike natural images, their inherently symbolic and abstract nature poses significant challenges for Multimodal Large Language Models (MLLMs). However, current benchmarks conflate perceptual and reasoning tasks, making it difficult to assess whether MLLMs genuinely understand mathematical diagrams beyond superficial pattern recognition. To address this gap, we introduce MATHGLANCE, a benchmark specifically designed to isolate and evaluate mathematical perception in MLLMs. MATHGLANCE comprises 1.2K images and 1.6K carefully curated questions spanning four perception tasks: shape classification, object counting, relationship identification, and object grounding, covering diverse domains including plane geometry, solid geometry, and graphical representations. Our evaluation of MLLMs reveals that their ability to understand diagrams is notably limited, particularly in fine-grained grounding tasks. In response, we construct GeoPeP, a perception-oriented dataset of 200K structured geometry image-text pairs explicitly annotated with geometric primitives and precise spatial relationships. Training MLLM on GeoPeP leads to significant gains in perceptual accuracy, which in turn substantially improves mathematical reasoning. Our benchmark and dataset establish critical standards for evaluating and advancing multimodal mathematical understanding, providing valuable resources and insights to foster future MLLM research.

Analytic DAG Constraints for Differentiable DAG Learning

Recovering the underlying Directed Acyclic Graph (DAG) structures from observational data presents a formidable challenge, partly due to the combinatorial nature of the DAG-constrained optimization problem. Recently, researchers have identified gradient vanishing as one of the primary obstacles in differentiable DAG learning and have proposed several DAG constraints to mitigate this issue. By developing the necessary theory to establish a connection between analytic functions and DAG constraints, we demonstrate that analytic functions from the set $\{f(x) = c_0 + \sum_{i=1}^{\infty}c_ix^i | \forall i > 0, c_i > 0; r = \lim_{i\rightarrow \infty}c_{i}/c_{i+1} > 0\}$ can be employed to formulate effective DAG constraints. Furthermore, we establish that this set of functions is closed under several functional operators, including differentiation, summation, and multiplication. Consequently, these operators can be leveraged to create novel DAG constraints based on existing ones. Using these properties, we design a series of DAG constraints and develop an efficient algorithm to evaluate them. Experiments in various settings demonstrate that our DAG constraints outperform previous state-of-the-art comparators. Our implementation is available at https://github.com/zzhang1987/AnalyticDAGLearning.

Frame-wise Conditioning Adaptation for Fine-Tuning Diffusion Models in Text-to-Video Prediction

Text-video prediction (TVP) is a downstream video generation task that requires a model to produce subsequent video frames given a series of initial video frames and text describing the required motion. In practice TVP methods focus on a particular category of videos depicting manipulations of objects carried out by human beings or robot arms. Previous methods adapt models pre-trained on text-to-image tasks, and thus tend to generate video that lacks the required continuity. A natural progression would be to leverage more recent pre-trained text-to-video (T2V) models. This approach is rendered more challenging by the fact that the most common fine-tuning technique, low-rank adaptation (LoRA), yields undesirable results. In this work, we propose an adaptation-based strategy we label Frame-wise Conditioning Adaptation (FCA). Within the module, we devise a sub-module that produces frame-wise text embeddings from the input text, which acts as an additional text condition to aid generation. We use FCA to fine-tune the T2V model, which incorporates the initial frame(s) as an extra condition. We compare and discuss the more effective strategy for injecting such embeddings into the T2V model. We conduct extensive ablation studies on our design choices with quantitative and qualitative performance analysis. Our approach establishes a new state-of-the-art for the task of TVP. The project page is at https://github.com/Cuberick-Orion/FCA .

Prosody-Enhanced Acoustic Pre-training and Acoustic-Disentangled Prosody Adapting for Movie Dubbing

Movie dubbing describes the process of transforming a script into speech that aligns temporally and emotionally with a given movie clip while exemplifying the speaker's voice demonstrated in a short reference audio clip. This task demands the model bridge character performances and complicated prosody structures to build a high-quality video-synchronized dubbing track. The limited scale of movie dubbing datasets, along with the background noise inherent in audio data, hinder the acoustic modeling performance of trained models. To address these issues, we propose an acoustic-prosody disentangled two-stage method to achieve high-quality dubbing generation with precise prosody alignment. First, we propose a prosody-enhanced acoustic pre-training to develop robust acoustic modeling capabilities. Then, we freeze the pre-trained acoustic system and design a disentangled framework to model prosodic text features and dubbing style while maintaining acoustic quality. Additionally, we incorporate an in-domain emotion analysis module to reduce the impact of visual domain shifts across different movies, thereby enhancing emotion-prosody alignment. Extensive experiments show that our method performs favorably against the state-of-the-art models on two primary benchmarks. The demos are available at https://zzdoog.github.io/ProDubber/.

I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?

The remarkable achievements of large language models (LLMs) have led many to conclude that they exhibit a form of intelligence. This is as opposed to explanations of their capabilities based on their ability to perform relatively simple manipulations of vast volumes of data. To illuminate the distinction between these explanations, we introduce a novel generative model that generates tokens on the basis of human interpretable concepts represented as latent discrete variables. Under mild conditions, even when the mapping from the latent space to the observed space is non-invertible, we establish an identifiability result: the representations learned by LLMs through next-token prediction can be approximately modeled as the logarithm of the posterior probabilities of these latent discrete concepts, up to an invertible linear transformation. This theoretical finding not only provides evidence that LLMs capture underlying generative factors, but also strongly reinforces the linear representation hypothesis, which posits that LLMs learn linear representations of human-interpretable concepts. Empirically, we validate our theoretical results through evaluations on both simulation data and the Pythia, Llama, and DeepSeek model families.

Interactive Medical Image Analysis with Concept-based Similarity Reasoning

The ability to interpret and intervene model decisions is important for the adoption of computer-aided diagnosis methods in clinical workflows. Recent concept-based methods link the model predictions with interpretable concepts and modify their activation scores to interact with the model. However, these concepts are at the image level, which hinders the model from pinpointing the exact patches the concepts are activated. Alternatively, prototype-based methods learn representations from training image patches and compare these with test image patches, using the similarity scores for final class prediction. However, interpreting the underlying concepts of these patches can be challenging and often necessitates post-hoc guesswork. To address this issue, this paper introduces the novel Concept-based Similarity Reasoning network (CSR), which offers (i) patch-level prototype with intrinsic concept interpretation, and (ii) spatial interactivity. First, the proposed CSR provides localized explanation by grounding prototypes of each concept on image regions. Second, our model introduces novel spatial-level interaction, allowing doctors to engage directly with specific image areas, making it an intuitive and transparent tool for medical imaging. CSR improves upon prior state-of-the-art interpretable methods by up to 4.5\% across three biomedical datasets. Our code is released at https://github.com/tadeephuy/InteractCSR.

RandLoRA: Full-rank parameter-efficient fine-tuning of large models

Low-Rank Adaptation (LoRA) and its variants have shown impressive results in reducing the number of trainable parameters and memory requirements of large transformer networks while maintaining fine-tuning performance. However, the low-rank nature of the weight update inherently limits the representation power of fine-tuned models, potentially compromising performance on complex tasks. This raises a critical question: when a performance gap between LoRA and standard fine-tuning is observed, is it due to the reduced number of trainable parameters or the rank deficiency? This paper aims to answer this question by introducing RandLoRA, a parameter-efficient method that performs full-rank updates using a learned linear combinations of low-rank, non-trainable random matrices. Our method limits the number of trainable parameters by restricting optimization to diagonal scaling matrices applied to the fixed random matrices. This allows us to effectively overcome the low-rank limitations while maintaining parameter and memory efficiency during training. Through extensive experimentation across vision, language, and vision-language benchmarks, we systematically evaluate the limitations of LoRA and existing random basis methods. Our findings reveal that full-rank updates are beneficial across vision and language tasks individually, and even more so for vision-language tasks, where RandLoRA significantly reduces -- and sometimes eliminates -- the performance gap between standard fine-tuning and LoRA, demonstrating its efficacy.

Open Eyes, Then Reason: Fine-grained Visual Mathematical Understanding in MLLMs

Current multimodal large language models (MLLMs) often underperform on mathematical problem-solving tasks that require fine-grained visual understanding. The limitation is largely attributable to inadequate perception of geometric primitives during image-level contrastive pre-training (e.g., CLIP). While recent efforts to improve math MLLMs have focused on scaling up mathematical visual instruction datasets and employing stronger LLM backbones, they often overlook persistent errors in visual recognition. In this paper, we systematically evaluate the visual grounding capabilities of state-of-the-art MLLMs and reveal a significant negative correlation between visual grounding accuracy and problem-solving performance, underscoring the critical role of fine-grained visual understanding. Notably, advanced models like GPT-4o exhibit a 70% error rate when identifying geometric entities, highlighting that this remains a key bottleneck in visual mathematical reasoning. To address this, we propose a novel approach, SVE-Math (Selective Vision-Enhanced Mathematical MLLM), featuring a geometric-grounded vision encoder and a feature router that dynamically adjusts the contribution of hierarchical visual feature maps. Our model recognizes accurate visual primitives and generates precise visual prompts tailored to the language model's reasoning needs. In experiments, SVE-Math-Qwen2.5-7B outperforms other 7B models by 15% on MathVerse and is compatible with GPT-4V on MathVista. Despite being trained on smaller datasets, SVE-Math-7B achieves competitive performance on GeoQA, rivaling models trained on significantly larger datasets. Our findings emphasize the importance of incorporating fine-grained visual understanding into MLLMs and provide a promising direction for future research.

EmoDubber: Towards High Quality and Emotion Controllable Movie Dubbing

Given a piece of text, a video clip, and a reference audio, the movie dubbing task aims to generate speech that aligns with the video while cloning the desired voice. The existing methods have two primary deficiencies: (1) They struggle to simultaneously hold audio-visual sync and achieve clear pronunciation; (2) They lack the capacity to express user-defined emotions. To address these problems, we propose EmoDubber, an emotion-controllable dubbing architecture that allows users to specify emotion type and emotional intensity while satisfying high-quality lip sync and pronunciation. Specifically, we first design Lip-related Prosody Aligning (LPA), which focuses on learning the inherent consistency between lip motion and prosody variation by duration level contrastive learning to incorporate reasonable alignment. Then, we design Pronunciation Enhancing (PE) strategy to fuse the video-level phoneme sequences by efficient conformer to improve speech intelligibility. Next, the speaker identity adapting module aims to decode acoustics prior and inject the speaker style embedding. After that, the proposed Flow-based User Emotion Controlling (FUEC) is used to synthesize waveform by flow matching prediction network conditioned on acoustics prior. In this process, the FUEC determines the gradient direction and guidance scale based on the user's emotion instructions by the positive and negative guidance mechanism, which focuses on amplifying the desired emotion while suppressing others. Extensive experimental results on three benchmark datasets demonstrate favorable performance compared to several state-of-the-art methods.