arXiv subjects

Cihang Xie

Publications and source records attributed to Cihang Xie.

At least 55 records · Page 3Linked to original sources

arXiv2026

MedFrameQA: A Multi-Image Medical VQA Benchmark for Clinical Reasoning

Real-world clinical practice demands multi-image comparative reasoning, yet current medical benchmarks remain limited to single-frame interpretation. We present MedFrameQA, the first benchmark explicitly designed to test multi-image medical VQA through educationally-validated diagnostic sequences. To construct this dataset, we develop a scalable pipeline that leverages narrative transcripts from medical education videos to align visual frames with textual concepts, automatically producing 2,851 high-quality multi-image VQA pairs with explicit, transcript-grounded reasoning chains. Our evaluation of 11 advanced MLLMs (including reasoning models) exposes severe deficiencies in multi-image synthesis, where accuracies mostly fall below 50% and exhibit instability across varying image counts. Error analysis demonstrates that models often treat images as isolated instances, failing to track pathological progression or cross-reference anatomical shifts. MedFrameQA provides a rigorous standard for evaluating the next generation of MLLMs in handling complex, temporally grounded medical narratives.

cs.CV↗

arXiv2026

Spiral RoPE: Rotate Your Rotary Positional Embeddings in the 2D Plane

Rotary Position Embedding (RoPE) is the de facto positional encoding in large language models due to its ability to encode relative positions and support length extrapolation. When adapted to vision transformers, the standard axial formulation decomposes two-dimensional spatial positions into horizontal and vertical components, implicitly restricting positional encoding to axis-aligned directions. We identify this directional constraint as a fundamental limitation of the standard axial 2D RoPE, which hinders the modeling of oblique spatial relationships that naturally exist in natural images. To overcome this limitation, we propose Spiral RoPE, a simple yet effective extension that enables multi-directional positional encoding by partitioning embedding channels into multiple groups associated with uniformly distributed directions. Each group is rotated according to the projection of the patch position onto its corresponding direction, allowing spatial relationships to be encoded beyond the horizontal and vertical axes. Across a wide range of vision tasks including classification, segmentation, and generation, Spiral RoPE consistently improves performance. Qualitative analysis of attention maps further show that Spiral RoPE exhibits more concentrated activations on semantically relevant objects and better respects local object boundaries, highlighting the importance of multi-directional positional encoding in vision transformers.

cs.CV↗

arXiv2026

SimpleMem: Efficient Lifelong Memory for LLM Agents

To support long-term interaction in complex environments, LLM agents require memory systems that manage historical experiences. Existing approaches either retain full interaction histories via passive context extension, leading to substantial redundancy, or rely on iterative reasoning to filter noise, incurring high token costs. To address this challenge, we introduce SimpleMem, an efficient memory framework based on semantic lossless compression. We propose a three-stage pipeline designed to maximize information density and token utilization: (1) Semantic Structured Compression, which distills unstructured interactions into compact, multi-view indexed memory units; (2) Online Semantic Synthesis, an intra-session process that instantly integrates related context into unified abstract representations to eliminate redundancy; and (3) Intent-Aware Retrieval Planning, which infers search intent to dynamically determine retrieval scope and construct precise context efficiently. Experiments on benchmark datasets show that our method consistently outperforms baseline approaches in accuracy, retrieval efficiency, and inference cost, achieving an average F1 improvement of 26.4% in LoCoMo while reducing inference-time token consumption by up to 30-fold, demonstrating a superior balance between performance and efficiency. Code is available at https://github.com/aiming-lab/SimpleMem.

cs.AI↗

arXiv2025

A Definition of AGI

The lack of a concrete definition for Artificial General Intelligence (AGI) obscures the gap between today's specialized AI and human-level cognition. This paper introduces a quantifiable framework to address this, defining AGI as matching the cognitive versatility and proficiency of a well-educated adult. To operationalize this, we ground our methodology in Cattell-Horn-Carroll theory, the most empirically validated model of human cognition. The framework dissects general intelligence into ten core cognitive domains-including reasoning, memory, and perception-and adapts established human psychometric batteries to evaluate AI systems. Application of this framework reveals a highly "jagged" cognitive profile in contemporary models. While proficient in knowledge-intensive domains, current AI systems have critical deficits in foundational cognitive machinery, particularly long-term memory storage. The resulting AGI scores (e.g., GPT-4 at 27%, GPT-5 at 57%) concretely quantify both rapid progress and the substantial gap remaining before AGI.

cs.AI↗

arXiv2025

VQ-VA World: Towards High-Quality Visual Question-Visual Answering

This paper studies Visual Question-Visual Answering (VQ-VA): generating an image, rather than text, in response to a visual question -- an ability that has recently emerged in proprietary systems such as NanoBanana and GPT-Image. To also bring this capability to open-source models, we introduce VQ-VA World, a data-centric framework built around an agentic pipeline for large-scale, targeted data construction. Leveraging web-scale deployment, this pipeline crawls a massive amount of ~1.8M high-quality, interleaved image-text samples for model training. For evaluation, we further release IntelligentBench, a human-curated benchmark that systematically assesses VQ-VA along the aspects of world knowledge, design knowledge, and reasoning. Training with VQ-VA World data yields strong empirical gains: it helps LightFusion attain 53.06 on IntelligentBench, substantially surpassing the best prior open-source baselines (i.e., 7.78 from vanilla LightFusion; 1.94 from UniWorld-V1), and significantly narrowing the gap toward leading proprietary systems (e.g., 81.67 from NanoBanana; 82.64 from GPT-Image). By releasing the full suite of model weights, datasets, and pipelines, we hope to stimulate future research on VQ-VA.

cs.CV↗

arXiv2025

LightFusion: A Light-weighted, Double Fusion Framework for Unified Multimodal Understanding and Generation

Unified multimodal models have recently shown remarkable gains in both capability and versatility, yet most leading systems are still trained from scratch and require substantial computational resources. In this paper, we show that competitive performance can be obtained far more efficiently by strategically fusing publicly available models specialized for either generation or understanding. Our key design is to retain the original blocks while additionally interleaving multimodal self-attention blocks throughout the networks. This double fusion mechanism (1) effectively enables rich multi-modal fusion while largely preserving the original strengths of the base models, and (2) catalyzes synergistic fusion of high-level semantic representations from the understanding encoder with low-level spatial signals from the generation encoder. By training with only ~ 35B tokens, this approach achieves strong results across multiple benchmarks: 0.91 on GenEval for compositional text-to-image generation, 82.16 on DPG-Bench for complex text-to-image generation, 6.06 on GEditBench, and 3.77 on ImgEdit-Bench for image editing. By fully releasing the entire suite of code, model weights, and datasets, we hope to support future research on unified multimodal modeling.

cs.CV↗

arXiv2025

STAR-1: Safer Alignment of Reasoning LLMs with 1K Data

This paper introduces STAR-1, a high-quality, just-1k-scale safety dataset specifically designed for large reasoning models (LRMs) like DeepSeek-R1. Built on three core principles -- diversity, deliberative reasoning, and rigorous filtering -- STAR-1 aims to address the critical needs for safety alignment in LRMs. Specifically, we begin by integrating existing open-source safety datasets from diverse sources. Then, we curate safety policies to generate policy-grounded deliberative reasoning samples. Lastly, we apply a GPT-4o-based safety scoring system to select training examples aligned with best practices. Experimental results show that fine-tuning LRMs with STAR-1 leads to an average 40% improvement in safety performance across four benchmarks, while only incurring a marginal decrease (e.g., an average of 1.1%) in reasoning ability measured across five reasoning tasks. Extensive ablation studies further validate the importance of our design principles in constructing STAR-1 and analyze its efficacy across both LRMs and traditional LLMs. Our project page is https://ucsc-vlaa.github.io/STAR-1.

cs.CL↗

arXiv2025

When Visualizing is the First Step to Reasoning: MIRA, a Benchmark for Visual Chain-of-Thought

We propose MIRA, a new benchmark designed to evaluate models in scenarios where generating intermediate visual images is essential for successful reasoning. Unlike traditional CoT methods that rely solely on text, tasks in MIRA require models to generate and utilize intermediate images - such as sketches, structural diagrams, or path drawings - to guide their reasoning process. This setup closely mirrors how humans solve complex problems through "drawing to think". To solve this, MIRA focuses on tasks that are intrinsically challenging and involve complex structures, spatial relationships, or reasoning steps that are difficult to express through language alone. To ensure that our evaluation data is of high-quality, we include 546 multimodal problems, annotated with intermediate visual images and final answers. We also propose a unified evaluation protocol for MIRA that spans three levels of evaluation input: direct input with image and question only, text-only CoT input with image and thinking prompts, and Visual-CoT input with both annotated image clues and textual thinking prompts. To probe the upper bound of model capacity on our benchmark, we also report pass@k and majority voting accuracies under different k settings. Experimental results show that existing multimodal large language models, including strongest private models as well as strong open-weight models, perform poorly when relying solely on textual prompts. However, when intermediate visual cues are provided, model performance improves consistently, yielding an average relative gain of 33.7% across all models and tasks. We also probe the upper bound by expanding the search space and designing textual prompts aligned with Visual-CoT, but both yield only limited improvements compared to our Visual-CoT setting. These results underscore the critical role of imagined visual information in enabling successful reasoning on MIRA.

cs.CV↗

arXiv2025

Where on Earth? A Vision-Language Benchmark for Probing Model Geolocation Skills Across Scales

Vision-language models (VLMs) have advanced rapidly, yet their capacity for image-grounded geolocation in open-world conditions, a task that is challenging and of demand in real life, has not been comprehensively evaluated. We present EarthWhere, a comprehensive benchmark for VLM image geolocation that evaluates visual recognition, step-by-step reasoning, and evidence use. EarthWhere comprises 810 globally distributed images across two complementary geolocation scales: WhereCountry (i.e., 500 multiple-choice question-answering, with country-level answer and panoramas) and WhereStreet (i.e., 310 fine-grained street-level identification tasks requiring multi-step reasoning with optional web search). For evaluation, we adopt the final-prediction metrics: location accuracies within k km (Acc@k) for coordinates and hierarchical path scores for textual localization. Beyond this, we propose to explicitly score intermediate reasoning chains using human-verified key visual clues and a Shapley-reweighted thinking score that attributes credit to each clue's marginal contribution. We benchmark 13 state-of-the-art VLMs with web searching tools on our EarthWhere and report different types of final answer accuracies as well as the calibrated model thinking scores. Overall, Gemini-2.5-Pro achieves the best average accuracy at 56.32%, while the strongest open-weight model, GLM-4.5V, reaches 34.71%. We reveal that web search and reasoning do not guarantee improved performance when visual clues are limited, and models exhibit regional biases, achieving up to 42.7% higher scores in certain areas than others. These findings highlight not only the promise but also the persistent challenges of models to mitigate bias and achieve robust, fine-grained localization. We open-source our benchmark at https://github.com/UCSC-VLAA/EarthWhere.

cs.CV↗

arXiv2025

AHELM: A Holistic Evaluation of Audio-Language Models

Evaluations of audio-language models (ALMs) -- multimodal models that take interleaved audio and text as input and output text -- are hindered by the lack of standardized benchmarks; most benchmarks measure only one or two capabilities and omit evaluative aspects such as fairness or safety. Furthermore, comparison across models is difficult as separate evaluations test a limited number of models and use different prompting methods and inference parameters. To address these shortfalls, we introduce AHELM, a benchmark that aggregates various datasets -- including 2 new synthetic audio-text datasets called PARADE, which evaluates the ALMs on avoiding stereotypes, and CoRe-Bench, which measures reasoning over conversational audio through inferential multi-turn question answering -- to holistically measure the performance of ALMs across 10 aspects we have identified as important to the development and usage of ALMs: audio perception, knowledge, reasoning, emotion detection, bias, fairness, multilinguality, robustness, toxicity, and safety. We also standardize the prompts, inference parameters, and evaluation metrics to ensure equitable comparisons across models. We test 14 open-weight and closed-API ALMs from 3 developers and 3 additional simple baseline systems each consisting of an automatic speech recognizer and a language model. Our results show that while Gemini 2.5 Pro ranks top in 5 out of 10 aspects, it exhibits group unfairness ($p=0.01$) on ASR tasks whereas most of the other models do not. We also find that the baseline systems perform reasonably well on AHELM, with one ranking 6th overall despite having only speech-to-text capabilities. For transparency, all raw prompts, model generations, and outputs are available on our website at https://crfm.stanford.edu/helm/audio/v1.0.0. AHELM is intended to be a living benchmark and new datasets and models will be added over time.

cs.AI↗

arXiv2025

OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning

This paper provides a simplification on OpenVision's architecture and loss design for enhancing its training efficiency. Following the prior vision-language pretraining works CapPa and AIMv2, as well as modern multimodal designs like LLaVA, our changes are straightforward: we remove the text encoder (and therefore the contrastive loss), retaining only the captioning loss as a purely generative training signal. We name this new version OpenVision 2. The initial results are promising: despite this simplification, OpenVision 2 competitively matches the original model's performance on a broad set of multimodal benchmarks while substantially cutting both training time and memory consumption. For example, with ViT-L/14, it reduces training time by about 1.5x (from 83h to 57h), and memory usage by about 1.8x (from 24.5GB to 13.8GB, equivalently allowing the maximum batch size to grow from 2k to 8k). This superior training efficiency also allows us to scale far beyond the largest vision encoder used in OpenVision, reaching more than 1 billion parameters. We hold a strong belief that this lightweight, generative-only paradigm is compelling for future vision encoder development in multimodal foundation models.

cs.CV↗

arXiv2025

VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges

Recent advancements in large-scale video-language models have shown significant potential for real-time planning and detailed interactions. However, their high computational demands and the scarcity of annotated datasets limit their practicality for academic researchers. In this work, we introduce VideoLLaMB, a novel and efficient framework for long video understanding that leverages recurrent memory bridges and temporal memory tokens to enable seamless encoding of entire video sequences with preserved semantic continuity. Central to our approach is a SceneTiling algorithm that segments videos into coherent semantic units, facilitating robust understanding across tasks without requiring additional training. VideoLLaMB achieves state-of-the-art performance, surpassing existing models by 4.2 points on four VideoQA benchmarks and by 2.06 points on egocentric planning tasks. Notably, it maintains strong performance under extreme video length scaling (up to 8 times) and excels at fine-grained frame retrieval on our proposed Needle in a Video Haystack (NIAVH) benchmark. With linear GPU memory scaling, VideoLLaMB processes up to 320 frames using a single Nvidia A100 GPU, despite being trained on only 16 frames-offering an unprecedented balance of accuracy, scalability, and cost-effectiveness. This makes it highly accessible and practical for the academic community.

cs.CV↗

arXiv2025

GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset

Recent advancements in large multimodal models like GPT-4o have set a new standard for high-fidelity, instruction-guided image editing. However, the proprietary nature of these models and their training data creates a significant barrier for open-source research. To bridge this gap, we introduce GPT-IMAGE-EDIT-1.5M, a publicly available, large-scale image-editing corpus containing more than 1.5 million high-quality triplets (instruction, source image, edited image). We systematically construct this dataset by leveraging the versatile capabilities of GPT-4o to unify and refine three popular image-editing datasets: OmniEdit, HQ-Edit, and UltraEdit. Specifically, our methodology involves 1) regenerating output images to enhance visual quality and instruction alignment, and 2) selectively rewriting prompts to improve semantic clarity. To validate the efficacy of our dataset, we fine-tune advanced open-source models on GPT-IMAGE-EDIT-1.5M. The empirical results are exciting, e.g., the fine-tuned FluxKontext achieves highly competitive performance across a comprehensive suite of benchmarks, including 7.24 on GEdit-EN, 3.80 on ImgEdit-Full, and 8.78 on Complex-Edit, showing stronger instruction following and higher perceptual quality while maintaining identity. These scores markedly exceed all previously published open-source methods and substantially narrow the gap to leading proprietary models. We hope the full release of GPT-IMAGE-EDIT-1.5M can help to catalyze further open research in instruction-guided image editing.

cs.CV↗

arXiv2025

MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine

This paper introduces MedTrinity-25M, a comprehensive, large-scale multimodal dataset for medicine, covering over 25 million images across 10 modalities with multigranular annotations for more than 65 diseases. These multigranular annotations encompass both global information, such as modality and organ detection, and local information like ROI analysis, lesion texture, and region-wise correlations. Unlike the existing multimodal datasets, which are limited by the availability of image-text pairs, we have developed the first automated pipeline that scales up multimodal data by generating multigranular visual and textual annotations in the form of image-ROI-description triplets without the need for any paired text descriptions. Specifically, data from over 30 different sources have been collected, preprocessed, and grounded using domain-specific expert models to identify ROIs related to abnormal regions. We then build a comprehensive knowledge base and prompt multimodal large language models to perform retrieval-augmented generation with the identified ROIs as guidance, resulting in multigranular textual descriptions. Compared to existing datasets, MedTrinity-25M provides the most enriched annotations, supporting a comprehensive range of multimodal tasks such as captioning and report generation, as well as vision-centric tasks like classification and segmentation. We propose LLaVA-Tri by pretraining LLaVA on MedTrinity-25M, achieving state-of-the-art performance on VQA-RAD, SLAKE, and PathVQA, surpassing representative SOTA multimodal large language models. Furthermore, MedTrinity-25M can also be utilized to support large-scale pre-training of multimodal medical AI models, contributing to the development of future foundation models in the medical domain. We will make our dataset available.

cs.CV↗

arXiv2025

AQA-Bench: An Interactive Benchmark for Evaluating LLMs' Sequential Reasoning Ability

This paper introduces AQA-Bench, a novel benchmark to assess the sequential reasoning capabilities of large language models (LLMs) in algorithmic contexts, such as depth-first search (DFS). The key feature of our evaluation benchmark lies in its interactive evaluation protocol - for example, in DFS, the availability of each node's connected edge is contingent upon the model's traversal to that node, thereby necessitating the LLM's ability to effectively remember visited nodes and strategize subsequent moves considering the possible environmental feedback in the future steps. We comprehensively build AQA-Bench with three different algorithms, namely binary search, depth-first search, and breadth-first search, and to evaluate the sequential reasoning ability of 14 different LLMs. Our investigations reveal several interesting findings: (1) Closed-source models like GPT-4 and Gemini generally show much stronger sequential reasoning ability, significantly outperforming open-source LLMs. (2) Naively providing in-context examples may inadvertently hurt few-shot performance in an interactive environment due to over-fitting to examples. (3) Instead of using optimal steps from another test case as the in-context example, a very limited number of predecessor steps in the current test case following the optimal policy can substantially boost small models' performance. (4) The performance gap between weak models and strong models is greatly due to the incapability of weak models to start well. (5) The scaling correlation between performance and model size is not always significant, sometimes even showcasing an inverse trend. We hope our study can catalyze future work on advancing the understanding and enhancement of LLMs' capabilities in sequential reasoning. The code is available at https://github.com/UCSC-VLAA/AQA-Bench.

cs.CL↗

arXiv2025

ARFlow: Autoregressive Flow with Hybrid Linear Attention

Flow models are effective at progressively generating realistic images, but they generally struggle to capture long-range dependencies during the generation process as they compress all the information from previous time steps into a single corrupted image. To address this limitation, we propose integrating autoregressive modeling -- known for its excellence in modeling complex, high-dimensional joint probability distributions -- into flow models. During training, at each step, we construct causally-ordered sequences by sampling multiple images from the same semantic category and applying different levels of noise, where images with higher noise levels serve as causal predecessors to those with lower noise levels. This design enables the model to learn broader category-level variations while maintaining proper causal relationships in the flow process. During generation, the model autoregressively conditions the previously generated images from earlier denoising steps, forming a contextual and coherent generation trajectory. Additionally, we design a customized hybrid linear attention mechanism tailored to our modeling approach to enhance computational efficiency. Our approach, termed ARFlow, achieves 6.63 FID scores on ImageNet at 256 * 256 without classifier-free guidance, reaching 1.96 FID with classifier-free guidance 1.5, outperforming the previous flow-based model SiT's 2.06 FID. Extensive ablation studies demonstrate the effectiveness of our modeling strategy and chunk-wise attention design.

cs.CV↗

arXiv2025

Knowledge or Reasoning? A Close Look at How LLMs Think Across Domains

Recent advances in reasoning-enhanced Large Language Models such as OpenAI-o1/3 and DeepSeek-R1 have significantly improved performance on complex tasks. However, the quality and transparency of their internal reasoning processes remain underexplored. This work moves beyond the final-answer accuracy and investigates step-by-step reasoning in the medical and mathematical domains by explicitly decomposing the thinking trajectories into two parts: knowledge and reasoning. Specifically, we introduce a fine-grained evaluation framework that judges: (1) the correctness of knowledge used (measured by Knowledge Index (KI)) and (2) the quality of reasoning (measured by Information Gain (InfoGain)). Using this framework, we study R1-distilled and base Qwen models trained with supervised fine-tuning (SFT) and/or reinforcement learning (RL) in the medical and math domains. Three intriguing findings emerge: (1) The general reasoning abilities in R1-distilled models do not transfer effectively to the medical domain through either SFT or RL. (2) SFT raises final-answer accuracy in both domains, but often at the cost of reasoning quality: InfoGain drops by 38.9% on average compared with untrained models; In the medical domain, however, SFT remains crucial because domain knowledge is indispensable. (3) RL enhances medical reasoning by pruning inaccurate or irrelevant knowledge from reasoning paths, thereby improving both reasoning accuracy and knowledge correctness.

cs.CL↗

arXiv2025

Mamba-R: Vision Mamba ALSO Needs Registers

Similar to Vision Transformers, this paper identifies artifacts also present within the feature maps of Vision Mamba. These artifacts, corresponding to high-norm tokens emerging in low-information background areas of images, appear much more severe in Vision Mamba -- they exist prevalently even with the tiny-sized model and activate extensively across background regions. To mitigate this issue, we follow the prior solution of introducing register tokens into Vision Mamba. To better cope with Mamba blocks' uni-directional inference paradigm, two key modifications are introduced: 1) evenly inserting registers throughout the input token sequence, and 2) recycling registers for final decision predictions. We term this new architecture Mamba-R. Qualitative observations suggest, compared to vanilla Vision Mamba, Mamba-R's feature maps appear cleaner and more focused on semantically meaningful regions. Quantitatively, Mamba-R attains stronger performance and scales better. For example, on the ImageNet benchmark, our base-size Mamba-R attains 83.0% accuracy, significantly outperforming Vim-B's 81.8%; furthermore, we provide the first successful scaling to the large model size (i.e., with 341M parameters), attaining a competitive accuracy of 83.6% (84.5% if finetuned with 384x384 inputs). Additional validation on the downstream semantic segmentation task also supports Mamba-R's efficacy. Code is available at https://github.com/wangf3014/Mamba-Reg.

cs.CV↗