arXiv subjects

Ser-Nam Lim

Publications and source records attributed to Ser-Nam Lim.

At least 37 records · Page 2Linked to original sources

arXiv2025

When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding

Large Multimodal Models (LMMs) have achieved impressive progress in visual perception and reasoning. However, when confronted with visually ambiguous or non-semantic scene text, they often struggle to accurately spot and understand the content, frequently generating semantically plausible yet visually incorrect answers, which we refer to as semantic hallucination. In this work, we investigate the underlying causes of semantic hallucination and identify a key finding: Transformer layers in LLM with stronger attention focus on scene text regions are less prone to producing semantic hallucinations. Thus, we propose a training-free semantic hallucination mitigation framework comprising two key components: (1) ZoomText, a coarse-to-fine strategy that identifies potential text regions without external detectors; and (2) Grounded Layer Correction, which adaptively leverages the internal representations from layers less prone to hallucination to guide decoding, correcting hallucinated outputs for non-semantic samples while preserving the semantics of meaningful ones. To enable rigorous evaluation, we introduce TextHalu-Bench, a benchmark of 1,740 samples spanning both semantic and non-semantic cases, with manually curated question answer pairs designed to probe model hallucinations. Extensive experiments demonstrate that our method not only effectively mitigates semantic hallucination but also achieves strong performance on public benchmarks for scene text spotting and understanding.

cs.CV↗

arXiv2025

VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention

Current video generation models excel at short clips but fail to produce cohesive multi-shot narratives due to disjointed visual dynamics and fractured storylines. Existing solutions either rely on extensive manual scripting/editing or prioritize single-shot fidelity over cross-scene continuity, limiting their practicality for movie-like content. We introduce VideoGen-of-Thought (VGoT), a step-by-step framework that automates multi-shot video synthesis from a single sentence by systematically addressing three core challenges: (1) Narrative fragmentation: Existing methods lack structured storytelling. We propose dynamic storyline modeling, which turns the user prompt into concise shot drafts and then expands them into detailed specifications across five domains (character dynamics, background continuity, relationship evolution, camera movements, and HDR lighting) with self-validation to ensure logical progress. (2) Visual inconsistency: previous approaches struggle to maintain consistent appearance across shots. Our identity-aware cross-shot propagation builds identity-preserving portrait (IPP) tokens that keep character identity while allowing controlled trait changes (expressions, aging) required by the story. (3) Transition artifacts: Abrupt shot changes disrupt immersion. Our adjacent latent transition mechanisms implement boundary-aware reset strategies that process adjacent shots' features at transition points, enabling seamless visual flow while preserving narrative continuity. Combined in a training-free pipeline, VGoT surpasses strong baselines by 20.4\% in within-shot face consistency and 17.4\% in style consistency, while requiring 10x fewer manual adjustments. VGoT bridges the gap between raw visual synthesis and director-level storytelling for automated multi-shot video generation.

cs.CV↗

arXiv2025

CML-Bench: A Framework for Evaluating and Enhancing LLM-Powered Movie Scripts Generation

Large Language Models (LLMs) have demonstrated remarkable proficiency in generating highly structured texts. However, while exhibiting a high degree of structural organization, movie scripts demand an additional layer of nuanced storytelling and emotional depth-the 'soul' of compelling cinema-that LLMs often fail to capture. To investigate this deficiency, we first curated CML-Dataset, a dataset comprising (summary, content) pairs for Cinematic Markup Language (CML), where 'content' consists of segments from esteemed, high-quality movie scripts and 'summary' is a concise description of the content. Through an in-depth analysis of the intrinsic multi-shot continuity and narrative structures within these authentic scripts, we identified three pivotal dimensions for quality assessment: Dialogue Coherence (DC), Character Consistency (CC), and Plot Reasonableness (PR). Informed by these findings, we propose the CML-Bench, featuring quantitative metrics across these dimensions. CML-Bench effectively assigns high scores to well-crafted, human-written scripts while concurrently pinpointing the weaknesses in screenplays generated by LLMs. To further validate our benchmark, we introduce CML-Instruction, a prompting strategy with detailed instructions on character dialogue and event logic, to guide LLMs to generate more structured and cinematically sound scripts. Extensive experiments validate the effectiveness of our benchmark and demonstrate that LLMs guided by CML-Instruction generate higher-quality screenplays, with results aligned with human preferences.

cs.CV↗

arXiv2025

Scaling Up Temporal Domain Generalization via Temporal Experts Averaging

Temporal Domain Generalization (TDG) aims to generalize across temporal distribution shifts, e.g., lexical change over time. Prior work often addresses this by predicting future model weights. However, full model prediction is prohibitively expensive for even reasonably sized models. Thus, recent methods only predict the classifier layer, limiting generalization by failing to adjust other model components. To address this, we propose Temporal Experts Averaging (TEA), a novel and scalable TDG framework that updates the entire model using weight averaging to maximize generalization potential while minimizing computational costs. Our theoretical analysis guides us to two steps that enhance generalization to future domains. First, we create expert models with functional diversity yet parameter similarity by fine-tuning a domain-agnostic base model on individual temporal domains while constraining weight changes. Second, we optimize the bias-variance tradeoff through adaptive averaging coefficients derived from modeling temporal weight trajectories in a principal component subspace. Expert's contributions are based on their projected proximity to future domains. Extensive experiments across 7 TDG benchmarks, 5 models, and 2 TDG settings shows TEA outperforms prior TDG methods by up to 69% while being up to 60x more efficient.

cs.LG↗

arXiv2025

Delta Activations: A Representation for Finetuned Large Language Models

The success of powerful open source Large Language Models (LLMs) has enabled the community to create a vast collection of post-trained models adapted to specific tasks and domains. However, navigating and understanding these models remains challenging due to inconsistent metadata and unstructured repositories. We introduce Delta Activations, a method to represent finetuned models as vector embeddings by measuring shifts in their internal activations relative to a base model. This representation allows for effective clustering by domain and task, revealing structure in the model landscape. Delta Activations also demonstrate desirable properties: it is robust across finetuning settings and exhibits an additive property when finetuning datasets are mixed. In addition, we show that Delta Activations can embed tasks via few-shot finetuning, and further explore its use for model selection and merging. We hope Delta Activations can facilitate the practice of reusing publicly available models. Code is available at https://github.com/OscarXZQ/delta_activations.

cs.LG↗

arXiv2025

TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis

Audio-driven talking head synthesis has achieved remarkable photorealism, yet state-of-the-art (SOTA) models exhibit a critical failure: they lack generalization to the full spectrum of human diversity in ethnicity, language, and age groups. We argue that this generalization gap is a direct symptom of limitations in existing training data, which lack the necessary scale, quality, and diversity. To address this challenge, we introduce TalkVid, a new large-scale, high-quality, and diverse dataset containing 1244 hours of video from 7729 unique speakers. TalkVid is curated through a principled, multi-stage automated pipeline that rigorously filters for motion stability, aesthetic quality, and facial detail, and is validated against human judgments to ensure its reliability. Furthermore, we construct and release TalkVid-Bench, a stratified evaluation set of 500 clips meticulously balanced across key demographic and linguistic axes. Our experiments demonstrate that a model trained on TalkVid outperforms counterparts trained on previous datasets, exhibiting superior cross-dataset generalization. Crucially, our analysis on TalkVid-Bench reveals performance disparities across subgroups that are obscured by traditional aggregate metrics, underscoring its necessity for future research. Code and data can be found in https://github.com/FreedomIntelligence/TalkVid

cs.CV↗

arXiv2025

Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation

Recent advancements in video generation have enabled the creation of high-quality, visually compelling videos. However, generating videos that adhere to the laws of physics remains a critical challenge for applications requiring realism and accuracy. In this work, we propose PhysHPO, a novel framework for Hierarchical Cross-Modal Direct Preference Optimization, to tackle this challenge by enabling fine-grained preference alignment for physically plausible video generation. PhysHPO optimizes video alignment across four hierarchical granularities: a) Instance Level, aligning the overall video content with the input prompt; b) State Level, ensuring temporal consistency using boundary frames as anchors; c) Motion Level, modeling motion trajectories for realistic dynamics; and d) Semantic Level, maintaining logical consistency between narrative and visuals. Recognizing that real-world videos are the best reflections of physical phenomena, we further introduce an automated data selection pipeline to efficiently identify and utilize "good data" from existing large-scale text-video datasets, thereby eliminating the need for costly and time-intensive dataset construction. Extensive experiments on both physics-focused and general capability benchmarks demonstrate that PhysHPO significantly improves physical plausibility and overall video generation quality of advanced models. To the best of our knowledge, this is the first work to explore fine-grained preference alignment and data selection for video generation, paving the way for more realistic and human-preferred video generation paradigms.

cs.CV↗

arXiv2025

Model Reveals What to Cache: Profiling-Based Feature Reuse for Video Diffusion Models

Recent advances in diffusion models have demonstrated remarkable capabilities in video generation. However, the computational intensity remains a significant challenge for practical applications. While feature caching has been proposed to reduce the computational burden of diffusion models, existing methods typically overlook the heterogeneous significance of individual blocks, resulting in suboptimal reuse and degraded output quality. To this end, we address this gap by introducing ProfilingDiT, a novel adaptive caching strategy that explicitly disentangles foreground and background-focused blocks. Through a systematic analysis of attention distributions in diffusion models, we reveal a key observation: 1) Most layers exhibit a consistent preference for either foreground or background regions. 2) Predicted noise shows low inter-step similarity initially, which stabilizes as denoising progresses. This finding inspires us to formulate a selective caching strategy that preserves full computation for dynamic foreground elements while efficiently caching static background features. Our approach substantially reduces computational overhead while preserving visual fidelity. Extensive experiments demonstrate that our framework achieves significant acceleration (e.g., 2.01 times speedup for Wan2.1) while maintaining visual fidelity across comprehensive quality metrics, establishing a viable method for efficient video generation.

cs.CV↗

arXiv2025

DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthiness

Document Visual Question Answering (VQA) demands robust integration of text detection, recognition, and spatial reasoning to interpret complex document layouts. In this work, we introduce DLaVA, a novel, training-free pipeline that leverages Multimodal Large Language Models (MLLMs) for zero-shot answer localization in order to improve trustworthiness, interpretability, and explainability. By leveraging an innovative OCR-free approach that organizes text regions with unique bounding box IDs, the proposed method preserves spatial contexts without relying on iterative OCR or chain-of-thought reasoning, thus substantially reducing the computational complexity. We further enhance the evaluation protocol by integrating Intersection over Union (IoU) metrics alongside Average Normalized Levenshtein Similarity (ANLS), thereby ensuring that not only textual accuracy is considered, but spatial accuracy is taken into account, ultimately reducing the risks of AI hallucinations and improving trustworthiness. Experiments on benchmark datasets demonstrate competitive performance compared to state-of-the-art techniques, with significantly lower computational complexity and enhanced accuracies and reliability for high-stakes applications. The code and datasets utilized in this study for DLaVA are accessible at: https://github.com/ahmad-shirazi/AnnotMLLM.

cs.CV↗

arXiv2025

AirSketch: Generative Motion to Sketch

Illustration is a fundamental mode of human expression and communication. Certain types of motion that accompany speech can provide this illustrative mode of communication. While Augmented and Virtual Reality technologies (AR/VR) have introduced tools for producing drawings with hand motions (air drawing), they typically require costly hardware and additional digital markers, thereby limiting their accessibility and portability. Furthermore, air drawing demands considerable skill to achieve aesthetic results. To address these challenges, we introduce the concept of AirSketch, aimed at generating faithful and visually coherent sketches directly from hand motions, eliminating the need for complicated headsets or markers. We devise a simple augmentation-based self-supervised training procedure, enabling a controllable image diffusion model to learn to translate from highly noisy hand tracking images to clean, aesthetically pleasing sketches, while preserving the essential visual cues from the original tracking data. We present two air drawing datasets to study this problem. Our findings demonstrate that beyond producing photo-realistic images from precise spatial inputs, controllable image diffusion can effectively produce a refined, clear sketch from a noisy input. Our work serves as an initial step towards marker-less air drawing and reveals distinct applications of controllable diffusion models to AirSketch and AR/VR in general.

cs.CV↗

arXiv2025

Niagara: Normal-Integrated Geometric Affine Field for Scene Reconstruction from a Single View

Recent advances in single-view 3D scene reconstruction have highlighted the challenges in capturing fine geometric details and ensuring structural consistency, particularly in high-fidelity outdoor scene modeling. This paper presents Niagara, a new single-view 3D scene reconstruction framework that can faithfully reconstruct challenging outdoor scenes from a single input image for the first time. Our approach integrates monocular depth and normal estimation as input, which substantially improves its ability to capture fine details, mitigating common issues like geometric detail loss and deformation. Additionally, we introduce a geometric affine field (GAF) and 3D self-attention as geometry-constraint, which combines the structural properties of explicit geometry with the adaptability of implicit feature fields, striking a balance between efficient rendering and high-fidelity reconstruction. Our framework finally proposes a specialized encoder-decoder architecture, where a depth-based 3D Gaussian decoder is proposed to predict 3D Gaussian parameters, which can be used for novel view synthesis. Extensive results and analyses suggest that our Niagara surpasses prior SoTA approaches such as Flash3D in both single-view and dual-view settings, significantly enhancing the geometric accuracy and visual fidelity, especially in outdoor scenes.

cs.GR↗

arXiv2025

DreamMask: Boosting Open-vocabulary Panoptic Segmentation with Synthetic Data

Open-vocabulary panoptic segmentation has received significant attention due to its applicability in the real world. Despite claims of robust generalization, we find that the advancements of previous works are attributed mainly on trained categories, exposing a lack of generalization to novel classes. In this paper, we explore boosting existing models from a data-centric perspective. We propose DreamMask, which systematically explores how to generate training data in the open-vocabulary setting, and how to train the model with both real and synthetic data. For the first part, we propose an automatic data generation pipeline with off-the-shelf models. We propose crucial designs for vocabulary expansion, layout arrangement, data filtering, etc. Equipped with these techniques, our generated data could significantly outperform the manually collected web data. To train the model with generated data, a synthetic-real alignment loss is designed to bridge the representation gap, bringing noticeable improvements across multiple benchmarks. In general, DreamMask significantly simplifies the collection of large-scale training data, serving as a plug-and-play enhancement for existing methods. For instance, when trained on COCO and tested on ADE20K, the model equipped with DreamMask outperforms the previous state-of-the-art by a substantial margin of 2.1% mIoU.

cs.CV↗

arXiv2025

DetailCLIP: Detail-Oriented CLIP for Fine-Grained Tasks

In this paper, we introduce DetailCLIP: A Detail-Oriented CLIP to address the limitations of contrastive learning-based vision-language models, particularly CLIP, in handling detail-oriented and fine-grained tasks like segmentation. While CLIP and its variants excel in the global alignment of image and text representations, they often struggle to capture the fine-grained details necessary for precise segmentation. To overcome these challenges, we propose a novel framework that employs patch-level comparison of self-distillation and pixel-level reconstruction losses, enhanced with an attention-based token removal mechanism. This approach selectively retains semantically relevant tokens, enabling the model to focus on the image's critical regions aligned with the specific functions of our model, including textual information processing, patch comparison, and image reconstruction, ensuring that the model learns high-level semantics and detailed visual features. Our experiments demonstrate that DetailCLIP surpasses existing CLIP-based and traditional self-supervised learning (SSL) models in segmentation accuracy and exhibits superior generalization across diverse datasets. DetailCLIP represents a significant advancement in vision-language modeling, offering a robust solution for tasks that demand high-level semantic understanding and detailed feature extraction. https://github.com/KishoreP1/DetailCLIP.

cs.CV↗

arXiv2025

Frequency-Guided Masking for Enhanced Vision Self-Supervised Learning

We present a novel frequency-based Self-Supervised Learning (SSL) approach that significantly enhances its efficacy for pre-training. Prior work in this direction masks out pre-defined frequencies in the input image and employs a reconstruction loss to pre-train the model. While achieving promising results, such an implementation has two fundamental limitations as identified in our paper. First, using pre-defined frequencies overlooks the variability of image frequency responses. Second, pre-trained with frequency-filtered images, the resulting model needs relatively more data to adapt to naturally looking images during fine-tuning. To address these drawbacks, we propose FOurier transform compression with seLf-Knowledge distillation (FOLK), integrating two dedicated ideas. First, inspired by image compression, we adaptively select the masked-out frequencies based on image frequency responses, creating more suitable SSL tasks for pre-training. Second, we employ a two-branch framework empowered by knowledge distillation, enabling the model to take both the filtered and original images as input, largely reducing the burden of downstream tasks. Our experimental results demonstrate the effectiveness of FOLK in achieving competitive performance to many state-of-the-art SSL methods across various downstream tasks, including image classification, few-shot learning, and semantic segmentation.

cs.CV↗

arXiv2025

VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention

Current video generation models excel at short clips but fail to produce cohesive multi-shot narratives due to disjointed visual dynamics and fractured storylines. Existing solutions either rely on extensive manual scripting/editing or prioritize single-shot fidelity over cross-scene continuity, limiting their practicality for movie-like content. We introduce VideoGen-of-Thought (VGoT), a step-by-step framework that automates multi-shot video synthesis from a single sentence by systematically addressing three core challenges: (1) Narrative Fragmentation: Existing methods lack structured storytelling. We propose dynamic storyline modeling, which first converts the user prompt into concise shot descriptions, then elaborates them into detailed, cinematic specifications across five domains (character dynamics, background continuity, relationship evolution, camera movements, HDR lighting), ensuring logical narrative progression with self-validation. (2) Visual Inconsistency: Existing approaches struggle with maintaining visual consistency across shots. Our identity-aware cross-shot propagation generates identity-preserving portrait (IPP) tokens that maintain character fidelity while allowing trait variations (expressions, aging) dictated by the storyline. (3) Transition Artifacts: Abrupt shot changes disrupt immersion. Our adjacent latent transition mechanisms implement boundary-aware reset strategies that process adjacent shots' features at transition points, enabling seamless visual flow while preserving narrative continuity. VGoT generates multi-shot videos that outperform state-of-the-art baselines by 20.4% in within-shot face consistency and 17.4% in style consistency, while achieving over 100% better cross-shot consistency and 10x fewer manual adjustments than alternatives.

cs.CV↗

arXiv2025

Next Patch Prediction for Autoregressive Visual Generation

Autoregressive models, built based on the Next Token Prediction (NTP) paradigm, show great potential in developing a unified framework that integrates both language and vision tasks. Pioneering works introduce NTP to autoregressive visual generation tasks. In this work, we rethink the NTP for autoregressive image generation and extend it to a novel Next Patch Prediction (NPP) paradigm. Our key idea is to group and aggregate image tokens into patch tokens with higher information density. By using patch tokens as a more compact input sequence, the autoregressive model is trained to predict the next patch, significantly reducing computational costs. To further exploit the natural hierarchical structure of image data, we propose a multi-scale coarse-to-fine patch grouping strategy. With this strategy, the training process begins with a large patch size and ends with vanilla NTP where the patch size is 1$\times$1, thus maintaining the original inference process without modifications. Extensive experiments across a diverse range of model sizes demonstrate that NPP could reduce the training cost to around 0.6 times while improving image generation quality by up to 1.0 FID score on the ImageNet 256x256 generation benchmark. Notably, our method retains the original autoregressive model architecture without introducing additional trainable parameters or specifically designing a custom image tokenizer, offering a flexible and plug-and-play solution for enhancing autoregressive visual generation.

cs.CV↗

arXiv2025

Temporal Regularization Makes Your Video Generator Stronger

Temporal quality is a critical aspect of video generation, as it ensures consistent motion and realistic dynamics across frames. However, achieving high temporal coherence and diversity remains challenging. In this work, we explore temporal augmentation in video generation for the first time, and introduce FluxFlow for initial investigation, a strategy designed to enhance temporal quality. Operating at the data level, FluxFlow applies controlled temporal perturbations without requiring architectural modifications. Extensive experiments on UCF-101 and VBench benchmarks demonstrate that FluxFlow significantly improves temporal coherence and diversity across various video generation models, including U-Net, DiT, and AR-based architectures, while preserving spatial fidelity. These findings highlight the potential of temporal augmentation as a simple yet effective approach to advancing video generation quality.

cs.CV↗

arXiv2025

Beyond Generation: Unlocking Universal Editing via Self-Supervised Fine-Tuning

Recent advances in video generation have outpaced progress in video editing, which remains constrained by several limiting factors, namely: (a) the task's dependency on supervision severely limits generality, (b) an unnecessary artificial separation between the generation and editing task, and (c) the high computational costs of training a video model. In this work, we propose UES (Unlocking Universal Editing via Self-Supervision), a lightweight self-supervised fine-tuning strategy that transforms generation models into unified generation-editing systems through self-supervised semantic alignment. Our approach establishes a dual-conditioning mechanism where original video-text pairs jointly provide visual and textual semantics, enabling structured learning of intrinsic spatiotemporal correspondences. Key advantages include: (i) Universality through supervision-free adaptation to diverse editing tasks, (ii) Unification of generation and editing applicable to most text(+image)-to-video model, and (iii) Efficiency via lightweight fine-tune that reduces tunable parameters by 92.67%. To enable systematic evaluation, we introduce OmniBench-99, a comprehensive benchmark spanning 99 videos across humans/animals, environments, and objects, comprising 4 editing types and 8 scenarios. Extensive experiments show UES enables models without inherent editing capability to perform powerful and universal editing while preserving or even enhancing their original generation performance.

cs.CV↗