Caption
-
MemForest: Efficient Agent Memory Management via EventTree Partitioning and Progressive Merging
2026-09-08 05:30:30Junxi Wang, Te Sun, Jiayi Zhu, Chen Zhang, Siyuan Li, Xuyang Liu, Zichen Wen, Xiaobing Tu, Jinkui Ren, Xiantao Zhang, Ziqi Yuan, Linfeng ZhangAbstract
Agent memory systems have demonstrated significant potential in long-term dialogue, personalized assistants, and video understanding. However, continuously accumulated memory introduces substantial storage and retrieval costs during inference. To address this issue, we propose \textbf{MemForest}, a general memory compression framework adaptable to various agent memory systems. Specifically, MemForest partitions historical memory into event-centric units by leveraging global semantic similarity and local temporal continuity. For each unit, it constructs a maximum spanning tree, termed an EventTree, and progressively merges redundant memory nodes by selecting high-weight edges, reducing storage overhead. Furthermore, we introduce an anchor-guided propagation retrieval mechanism that retrieves relevant memory nodes from the temporal neighborhoods of key nodes, improving retrieval accuracy. Extensive experiments demonstrate the effectiveness of MemForest. Under the unimodal Mem0 framework, MemForest retains \textbf{97.1%} of the original performance while compressing \textbf{50%} of historical memory across three benchmarks (LoCoMo, LongMemEval, and PersonaMem), achieving a \textbf{1.89x} retrieval speedup. Under the multimodal M3-Agent framework, it preserves \textbf{99.7%} of the original performance with a \textbf{50%} compression ratio across two benchmarks (M3-Bench-robot and M3-Bench-web), achieving a \textbf{2.24x} retrieval speedup. \textcolor{RoyalBlue}{\textit{Our code is available at [this https URL.}}](this https URL.}})
Abstract (translated)
URL
https://arxiv.org/abs/2609.08273
PDF
-
CS-CLIP: Compositional Scene Graph-guided CLIP for Robust Compositional Reasoning
2026-09-08 04:37:06SeongJun Jeong, Minjoon Jung, Woo Suk Choi, Youwon Jang, Byoung-Tak ZhangAbstract
Vision-language models (VLMs) demonstrate strong performance across compositional reasoning benchmarks, which require reasoning over semantic perturbations of objects, attributes, relations, and their interactions. However, our controlled analysis reveals that existing compositionality-aware VLMs exhibit element-specific biases, often underperforming vanilla CLIP on certain compositional elements. To address this, we propose Compositional Scene Graph-guided CLIP (CS-CLIP), which uses scene graphs to identify compositional elements and construct structured negatives via selective masking. We further retain negatives that are most contradictory to the original caption, forcing the model to rely on compositional structure rather than surface cues. CS-CLIP achieves state-of-the-art compositional reasoning with robust performance across compositional elements. It also preserves general vision-language capabilities such as cross-modal retrieval and downstream visual reasoning, while requiring fewer training samples than prior methods.
Abstract (translated)
URL
https://arxiv.org/abs/2609.08242
PDF
-
Bridging the Semantic-Utility Gap in Multimodal RAG via Generator-in-the-Loop Alignment
2026-09-08 03:18:58Zhan-Lun Chang, Dong-Jun Han, Seyyedali Hosseinalipour, Mung Chiang, Christopher G. BrintonAbstract
Vision-language models (VLMs) augmented with retrieval-augmented generation (RAG) benefit from access to external evidence. However, standard retrievers and rerankers optimize for semantic similarity rather than answer utility, creating a preference gap: documents that appear relevant may not help the generator produce a correct answer. Motivated by this, we propose a two-stage generator-in-the-loop alignment framework that closes this gap without human document-level relevance annotations. Our framework consists of two stages: in Stage 1, a VLM generates a hypothetical text passage from the image-query pair, which is used as the retrieval query for dense text search, bridging the image-to-text modality gap. In Stage 2, a cross-encoder reranker adapted with low-rank adaptation (LoRA) is fine-tuned using answer-supervised preference pairs mined from the frozen VLM: given the dataset answer label, a candidate document is labeled positive if the VLM produces the correct answer when given that document as context, and negative otherwise. This generator-guided signal is compatible with multiple alignment loss functions, including contrastive (triplet) loss, pairwise direct preference optimization (DPO), and supervised fine-tuning (SFT), and supports periodic re-mining to refresh preference pairs as the reranker improves. Experiments on VQA-X and A-OKVQA with Qwen3.5-2B and Qwen3-VL-4B-Instruct show that our proposed framework consistently outperforms rank-order, random, and REPLUG-style likelihood baselines under various alignment losses and pool size settings, suggesting that answer-level generator feedback is an effective supervision signal for preference alignment.
Abstract (translated)
URL
https://arxiv.org/abs/2609.08188
PDF
-
SAFIRE: Safety-Critical Benchmark for Fine-grained Fire and Smoke Understanding in Multimodal LLMs
2026-09-07 17:59:50Pengfei Li, Naufal Suryanto, Sicheng Zhang, Mohammad Alsharid, Muzammal NaseerAbstract
Multimodal Large Language Models (MLLMs) show strong progress on vision-language tasks, yet their reliability in safety-critical settings remains underexplored. Fire-smoke understanding is central to public safety and disaster response, but most existing benchmarks lack diverse real-world scenarios and context-aware evaluation. We introduce SAFIRE, a large-scale benchmark for fire-smoke understanding in MLLMs, comprising 83K captioned images from 20 scenarios and 193K multiple-choice VQA (MCVQA) generated from a 9.7K-image subset, spanning 10 evaluation dimensions from basic perception to higher-order reasoning. A GPT-5.4-assisted multi-stage verification pipeline with MLLM majority voting ensures annotation quality. Evaluating ten open-source MLLMs (8B-38B) yields an average accuracy of 61.9%, exposing major gaps in safety-critical reasoning. We further show that adapting vision encoders with only 7% of our domain-specific data boosts fire-scene classification accuracy from 20.1% to 64.5%, indicating that carefully curated data can yield substantial gains even when data volume is limited. All datasets, models, and code are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.07823
PDF
-
Beyond Sparse Rewards: A New Benchmark and Structure-Aware Graph Alignment for Micro-Drama Understanding
2026-09-07 06:48:17Yixin Qin, Shi-Zhe Chen, Zhiqi Yu, Siyuan Cheng, Tao Cheng, Jinwen Luo, Zheng WeiAbstract
Micro-dramas, characterized by ultra-short durations and hyper-dense storylines, pose unique challenges for video understanding that conventional benchmarks fail to address. To bridge this gap, we introduce M-Drama, the first large-scale bilingual benchmark for micro-drama comprehension, featuring over 35K instances across 9,138 clips. Furthermore, while reinforcement learning can enhance VLMs on complex narratives, existing reward metrics often suffer from sparse and superficial signals, failing to capture intricate character identities and temporal structures. We propose SAGA (Structure-Aware Graph Alignment), a novel graph-matching reward function that models narratives as heterogeneous graphs. SAGA computes dense, rigorous rewards via decoupled semantic triplet and structural temporal matching. Extensive experiments on Qwen3-VL-8B-Instruct demonstrate that SAGA outperforms existing baselines, delivering substantial improvements in open-ended accuracy and summary quality, while maintaining competitive out-of-domain generalization. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.07107
PDF
-
Interpretable Temporal Video Reasoning with EventGraph and EventField
Abstract
We present a structured temporal video reasoning pipeline built around a discrete EventGraph, a continuous EventField, and a human-readable EventGlyph view. On a calibrated EPIC-KITCHENS subset of 10 videos and 50 temporal reasoning questions, EventField+Glyph achieves 0.98 overall accuracy, which is higher than the caption baseline by +0.40 (paired p = 1.1 \times 10^{-5}) and direct VLM-only QA by +0.20 (p = 0.0063) on this subset. We further evaluate annotation-source variations, including manual, heuristic, and heuristic+Gemini pipelines, and find that the best structured method stays above the caption baseline across settings. We also include cross-video pair benchmarking and an appendix gallery of glyph outputs for all studied videos. Overall, the results indicate that structured temporal representations can support both performance and inspectability by preserving symbolic structure, capturing temporal continuity, and providing human-readable diagnostics for video reasoning.
Abstract (translated)
URL
https://arxiv.org/abs/2609.13258
PDF
-
Where Does the Sound Go? Tracing Acoustic Information Loss in Audio-Conditioned LLMs
2026-09-05 04:24:16Song-ha Jo, Sehyun Lee, Soyoon Kim, Jaesik Choi, Sanghyuk ChoiAbstract
Audio-conditioned language models often underuse acoustic cues such as prosody, emotion, and non-speech sounds, raising the question of whether ASR-supervised frontends discard this information before it reaches the LM. We test whether the frontend is responsible by comparing Whisper-Tiny and Whisper-Small with EnCodec, DAC-VAE, and WavTokenizer in a shared Qwen3.5-4B audio-LM pipeline on ASR, emotion recognition, and sound captioning. Encoder replacement alone does not resolve this underuse: Whisper variants remain strongest overall, including on emotion and environmental sound captioning. To localize the failure, we trace task-relevant information through the encoder, projector, LM layers, and LM head. Linear probes and geometric analyses show that discriminative acoustic structure remains recoverable at the final LM layer, even when MCQA accuracy trails probe accuracy by up to 83 points. Because the answer format and decoding procedure are controlled, this task-dependent gap points to content-specific readout failure rather than generic format bias. LogitLens analyses and a targeted LM head intervention support the conclusion that acoustic underuse is not explained solely by encoder-side information loss and that readout alignment can be a dominant bottleneck.
Abstract (translated)
URL
https://arxiv.org/abs/2609.05871
PDF
-
Evaluation of MLLM-Agnostic Plug-and-Play Keyframe Selection Methods for Long Video Understanding
2026-09-04 21:05:20Dilip Sarkar, Md. Safayet Islam, Liang LiangAbstract
Multimodal large language models (MLLMs) cannot process every frame of a long video because of limitations in visual-token and computational budgets. Three primary approaches have been proposed to enhance their long-video understanding capabilities: (i) Retraining an MLLM on a large video corpus and/or extending its input length; (ii) Training an adapter for a specific MLLM that takes the entire video and the query as input and selects the most relevant video frames; and (iii) Developing a training-free, plug-and-play (PaP) adapter that is MLLM-agnostic. We refer to the third approach as PaP keyframe selection. A PaP method may use only candidate video frames without considering the query, or it may use both candidate video frames and the query. The first approach is prohibitively expensive. The second approach requires substantial training time and computational resources, but it is accessible to many because an adapter contains significantly fewer trainable parameters than an entire MLLM. The third approach has the lowest computational cost and is therefore broadly accessible. To the best of our knowledge, only five PaP methods have been reported within the past year. All of these methods have been evaluated on one or more video question-answering benchmarks and have demonstrated improvements in long-video understanding. However, the methods were evaluated on different benchmarks using different MLLMs. We present a comprehensive evaluation of these five methods using three MLLMs across three long-video understanding benchmarks. Our results show that QAaF achieves the best performance in 13 of the 15 aggregate evaluation settings, while FOCUS ranks second overall. These results provide a common experimental reference for comparing training-free keyframe-selection methods for MLLMs.
Abstract (translated)
URL
https://arxiv.org/abs/2609.13250
PDF
-
MM-IFEval-Pro: A Multilingual and Attack-Resistant Benchmark for Instruction-Following in Vision-Language Models
2026-09-04 08:18:00Changming Xiao, Zhenliang Ni, Jinhui He, Han Shu, Jie HuAbstract
As vision-language models (VLMs) rapidly advance in image understanding, cross-modal reasoning, and complex instruction execution, instruction-following capability has become a key indicator of their reliability and practicality. However, existing multimodal instruction-following benchmarks still suffer from limited language coverage and insufficient adversarial safety scenarios, making them inadequate for evaluating real-world multilingual and safety-sensitive settings. To address these gaps, we present MM-IFEval-Pro, a multimodal instruction-following benchmark covering Chinese and English tasks as well as diverse instruction hijacking cases. MM-IFEval-Pro includes 4 major task categories and 24 subcategories and 8 instruction categories with 52 subcategories, with each sample containing an average of 3.0 constraints to realistically simulate complex instruction scenarios. We further construct a reinforcement-learning training set enriched with Chinese and adversarial instructions, which significantly improves model performance on MM-IFEval-Pro and transfers effectively to other mainstream multimodal benchmarks, demonstrating strong cross-task and cross-language generalization.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04859
PDF
-
ICM-Bench: Person-Level Identity Reasoning in Multimodal Agents with Long-Term Memory
2026-09-03 19:58:51Shidu Ren, Yunze Liu, Xing Liu, Chi-Hao Wu, Enmin Zhou, Junxiao ShenAbstract
Long-horizon multimodal agents should remember not only what happened but also who participated. This capability depends on linking recurring faces, voices, names, person-associated objects, events, and social relations to consistent identities over time. Existing long-video and multimodal-agent benchmarks measure broad memory question answering, but they do not isolate the ability to maintain recurring person identities and reason over their cross-time relations. We introduce ICM-Bench (Identity-Centric Memory Benchmark), which, to the best of our knowledge, is the first benchmark specifically designed to evaluate identity-centric reasoning over long video memories in multimodal agents. The benchmark contains 839 synthetic clips spanning 141 minutes and 1,217 open-ended questions about six recurring adults in a one-year life album. A theme-configurable pipeline generates the video collection and associates each question with its target identities and traceable supporting evidence. We compare direct caption-memory baselines, memory-augmented agents, and graph-retrieval systems. Gemini 3.1 Pro achieves the highest overall accuracy of 74.0%, yet its score falls to 60.3% on questions that require long-term identity profiles. The results show that current systems recover many event-level memories but remain less reliable when evidence must be accumulated around a stable person.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04438
PDF
-
Seeing Before Synthesizing: VLM-Guided Transition Event Discovery for Weakly-Supervised Dense Video Captioning
2026-09-03 17:58:02Ye-Chan Kim, Seunghee Choi, SeungJu Cha, Si-Woo Kim, Hwiseon Kim, Hyungee Kim, Dong-Jin KimAbstract
Weakly-Supervised Dense Video Captioning aims to localize and describe multiple events in untrimmed videos given only an ordered set of event-level captions per video. Recent work synthesizes auxiliary transition captions via LLM to provide additional vision-language alignment, but these captions lack visual grounding and are rigidly assigned to every inter-event gap at a fixed location and duration. To address these, we propose Seeing Before Synthesizing (SBS), a framework that adaptively provides visually grounded linguistic guidance only where warranted. Leveraging a VLM, we generate frame-level narratives for the inter-event gaps and detect transitions from the semantic variation across them. For identified transitions, we then refine inter-event temporal masks by blending the temporal midpoint with the semantic change point and selecting the width that maximizes vision-language alignment. Experiments on ActivityNet Captions and YouCook2 demonstrate state-of-the-art performance in both captioning and localization.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04183
PDF
-
Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding
2026-09-03 17:28:14Hongyu Qu, Guangming Yao, Ling Xing, Xiaobin Hu, Rongxing Ding, Guibin Zhang, Fan Zhang, Yi Yuan, Xiangbo Shu, Shuicheng YanAbstract
Streaming video understanding requires multimodal large language models (MLLMs) to process continuous visual inputs and respond to user queries under strict causality and bounded memory. Existing approaches typically compress historical observations into an external memory bank and retrieve query-relevant evidence as additional visual context. Though effective, this store-and-retrieve paradigm keeps historical evidence as external visual context, preventing it from being internalized into a compact, evolving latent memory that can continuously guide streaming reasoning. To bridge this gap, we introduce LatentStream, a progressive latent working memory framework that shifts streaming memory from store-and-retrieve to retrieve-and-internalize. Specifically, LatentStream comprises three coordinated components. First, Query-agnostic Hierarchical Streaming Memory organizes visual history into short-, mid-, and long-term levels under a fixed memory budget through Jenks-guided adaptive consolidation. Once a query arrives, Hierarchical Latent Memory Evolution equips groups of latent memory tokens with progressively expanding memory receptive fields, enabling them to iteratively retrieve historical evidence from their corresponding scopes and internalize it into a compact, fixed-length latent memory. Finally, Progressive Confidence-guided Latent Memory Optimization constructs a hierarchical progression reward from group-wise predictive entropy and jointly refines the latent memory tokens and retrieved evidence, encouraging increasingly confident streaming reasoning. Extensive experiments demonstrate that LatentStream achieves new state-of-the-art results on existing online and offline video benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04131
PDF
-
SVG-Score: Human-Aligned Evaluation of Text-to-SVG Generation
2026-09-03 13:12:37Marco Cipriano, Leonardo Zini, Alexandra Schild, Valentin Teutschbein, Afsana Mimi, Marcella Cornia, Lorenzo Baraldi, Gerard de MeloAbstract
Scalable Vector Graphics (SVG) generation is attracting increasing attention as generative models improve in expressiveness and controllability. Progress, however, is held back by the lack of domain-specific evaluation protocols: current practice relies on metrics designed for natural images, most notably CLIPScore, which was never trained on vector graphics and aligns only partially with human judgment. We introduce \textbf{\ours}, a human-aligned evaluation framework for text-to-SVG generation. Through controlled caption and image perturbations, we first show that CLIP-based scores barely react to the errors SVG generators actually make, such as wrong colors, counts, and spatial relations, and that off-the-shelf Vision-Language Model (VLM) judges, while more sensitive, respond unevenly across error types and SVG styles. We then introduce a human-annotated dataset for \textit{Semantic Alignment}, measuring how faithfully a generated SVG reflects its caption. Building on it, we develop two complementary evaluators: CLIP scorers adapted to vector graphics and then aligned to human preferences, for fast large-scale evaluation, and a VLM judge trained with supervised fine-tuning and reward-shaped reinforcement learning, for more expressive and interpretable assessment. Using both, we benchmark major open-source, commercial, and optimization-based SVG generators on an independent caption set.
Abstract (translated)
URL
https://arxiv.org/abs/2609.03806
PDF
-
A Reverse Sign Language Dictionary: Open-Vocabulary Sign Recognition from Continuous Signing via Video Captioning and Description Retrieval
2026-09-03 12:59:40Santiago Poveda-Guti\'errez, Hideki Nakayama, Mayumi BonoAbstract
Isolated Sign Language Recognition (ISLR) is conventionally cast as closed-set classification over gloss labels, which cannot generalize to signs unseen in training and ties every deployment to a gloss-annotated lexicon. We instead recognize signs extracted from continuous signing by (1) captioning a sign-level clip into a free-form procedural description of the articulation with an open-weight vision-language model, and (2) retrieving the closest entry from a vocabulary of target descriptions with a multilingual sentence encoder: a reverse sign language dictionary that needs no gloss supervision and admits an open vocabulary. On 1,300 sign-level segments from a Japanese Sign Language (JSL) dialogue corpus annotated with procedural descriptions (against a 2% top-10 chance floor over the 503-entry target vocabulary), fine-tuning the captioner substantially improves seen-class retrieval: language and vision tower fine-tuning raises top-10 retrieval on seen classes from 4.5% (untrained) to 49%, becoming statistically indistinguishable from a standard supervised closed-set classifier (I3D) on two of the three test sets where a closed-set classifier can be evaluated at all. More importantly, unseen-class retrieval also improves significantly over the untrained pipeline (11.5% -> 21.0% top-10, p=0.0094), a regime in which the closed-set classifier cannot participate. A matcher-side empirical upper-bound analysis shows the sentence encoder already recovers close to 100% of paraphrased gold descriptions, locating a gap in captioning quality that we aim to address in future work. To our knowledge this is the first description-based, open-vocabulary sign lookup from continuous signing without gloss supervision, and the first for JSL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.03788
PDF
-
Understanding Autonomous Driving Datasets by Describing Differences between Image Subsets in Natural Language
2026-09-03 11:15:23Julian Truetsch, Felix Hauser, Christoph Stiller, Frank BiederAbstract
Understanding the composition of large-scale autonomous driving datasets is essential for safety, robustness, and reliable operation across domains. For example, domain shift between locations could lead to the operating environment being misaligned with the training data, resulting in potentially dangerous performance degradation. Yet, existing data analysis pipelines largely rely on metadata, predefined labels, or manual inspection, which provide limited semantic insight or do not scale. This paper studies set difference captioning: given two subsets of images, the goal is to produce a natural-language hypothesis describing differences between the target and reference set. Building on a two-stage formulation, we adapt the method to autonomous driving by focusing on object-centric patches derived from object detection, which simplifies aggregation and enables attribution of differences to specific object instances or categories. To evaluate this setting in-domain, we introduce a new benchmark, AD-Diff Bench. Low-concentration experiments assess the suitability of set-difference-captioning approaches to sparse, real-world differences. We restrict our experiments to open-weight models to support reproducibility and ease of deployment. The proposed benchmark and analysis provide a step towards practical, human-interpretable dataset introspection for autonomous driving datasets. Our implementation and benchmark dataset are available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2609.03677
PDF
-
CoFiE: Coarse-to-Fine Evidence Selection for Efficient Streaming Video Understanding
2026-09-03 11:14:21Jing Jiang, Yiran Ling, Ruonan Li, Dimitrios Stamoulis, Jie LiuAbstract
Streaming video understanding requires Vision Language Models (VLLMs) to process growing video streams and answer user questions under tight latency constraints. Existing methods improve efficiency through token pruning and memory-bank schemes, but mainly reduce visual tokens after visual encoding. Consequently, downstream token pruning alone cannot substantially reduce end-to-end latency because the expensive frame encoding cost has already been incurred. We propose CoFiE, a Coarse-to-Fine Evidence Selection framework that decouples evidence selection into a coarse, query-agnostic filtering stage before the vision encoder and a fine, query-specific refinement stage during LLM prefill. CoFiE introduces Novelty-Guided Frame Filtering to retain visually distinctive candidate frames and Query-Specific Evidence Refinement to select the frames most relevant to the user query. This design removes substantial redundancy before frame encoding while preserving query-specific refinement once semantic information becomes available. Experiments show that CoFiE establishes a new state-of-the-art accuracy-efficiency trade-off across multiple video understanding benchmarks, reaching 78.86% accuracy on StreamingBench and 68.72% on OvO-Bench, with improvements of up to 3.15% over prior methods. Even with up to 80% evidence-frame filtering, CoFiE outperforms strong open-source multimodal models while improving end-to-end inference latency by up to 2.54 times.
Abstract (translated)
URL
https://arxiv.org/abs/2609.03675
PDF
-
Text2Thermal: Physics-Aware Thermal Image Synthesis from Textual Priors
2026-09-03 09:33:09Tayeba Qazi, Brejesh Lall, Prerana MukherjeeAbstract
Thermal infrared imaging offers reliable perception in darkness and adverse weather, but thermal datasets remain scarce, motivating extensive work on translating abundant RGB images into thermal. Such translation is fundamentally ill-posed as thermal appearance is governed by surface emissivity and object temperature, neither of which is observable in the visible spectrum, so a single RGB image is consistent with many valid thermal outputs. We argue that language offers a natural means of resolving this ambiguity, and propose Text2Thermal, a framework for physics-aware thermal image synthesis from textual priors. Rather than inferring the unobservable radiometric factors from RGB, we supply them explicitly through thermally grounded captions encoding material, weather, time-of-day, and heat-emission state, and adapt a pretrained Stable Diffusion backbone to the thermal domain. Because the radiometric content is determined entirely by the prompt, Text2Thermal synthesizes thermal imagery without requiring a registered RGB image at inference; where spatial guidance is desired, an optional control signal imparts scene geometry without disturbing the prompt-specified radiometry. Experiments on M3FD, FLIR, and FMB show that Text2Thermal achieves state-of-the-art FID among thermal image synthesis methods while offering text-level control that translation-based approaches cannot provide.
Abstract (translated)
URL
https://arxiv.org/abs/2609.03585
PDF
-
Multi-scale Image Representation Compression
2026-09-02 21:44:26Tianhao Peng, Ho Man Kwan, Fan Zhang, Shan Liu, David BullAbstract
Overfitted codecs have demonstrated promising performance for image and video compression. In particular, for image compression, the Cool-chic family of models has shown competitive performance against scene-agnostic models, with orders of magnitude lower decoding complexity at the cost of a longer overfitting process. However, these overfitted image codecs are not fully optimized toward the rate-distortion objective: their network weights remain in full precision during training, and the associated quantization parameters are selected in a separate post-training stage. Furthermore, their synthesis operates at a single scale, which overlooks cross-scale redundancy. In this paper, we propose MIRC, an overfitted image codec in which every coded component, including the latents, the synthesis network, and the entropy models, is quantized and entropy coded under a single rate-distortion objective, adopting the end-to-end compression pipeline of the neural video representation codec NVRC. We further introduce a multi-scale representation with cross-stage parameter sharing, which improves coding efficiency at a small transmitted overhead. On the CLIC2020 professional validation set, MIRC achieves a 10.5% BD-rate saving against VVC (VTM 22.0). Moreover, MIRC offers a family of configurations spanning 1.2 to 2.9 kMAC per pixel, so the decoding budget can be selected to match the deployment target.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04274
PDF
-
SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models
2026-09-02 17:59:41Junchao Huang, Guian Fang, Shengju Qian, Xianghao Kong, Zhuoran Zhao, Wei Huang, Yihua Du, Zixin Zhang, Justin Cui, Yuchao Gu, Yukang Chen, Xinting Hu, Tianyu He, Shaoshuai Shi, Zhuotao Tian, Xin Wang, Mike Zheng Shou, Li JiangAbstract
We introduce SolarWM, a fully open foundation for building interactive video world models from data preparation through long-horizon inference. Training across heterogeneous data sources and video backbones is challenging: datasets differ in temporal scale, camera geometry, visual quality, motion, and captioning styles, while video generators use distinct representations and architectures. Naive data mixing and model-specific implementations therefore produce inconsistent supervision and make results difficult to reproduce and compare. SolarWM addresses this coupling with a reconfigurable multi-source data engine and a backbone-native adaptation framework. The engine converts 1.43 million canonical clips from 10 datasets into a unified, frame-aligned contract covering visual observations, metric camera geometry, captions, quality metadata, selection decisions, and provenance, while decoupling source processing from mixture construction. Under shared camera-conditioning, training, and inference interfaces, we instantiate four 5B--33B models based on Wan2.2, LTX-2.5, and MiniMax-H3 while preserving their native representations and objectives. A unified three-stage recipe combines bidirectional adaptation, teacher-forced autoregressive initialization, and distribution matching distillation. The resulting causal models enable real-time interaction over rollouts ranging from minutes to hours after being trained on only 5s sequences. By releasing the resulting data, pipeline, recipes, weights, and framework, SolarWM provides a reproducible and extensible foundation for interactive world-model research.
Abstract (translated)
URL
https://arxiv.org/abs/2609.02886
PDF
-
ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding
2026-09-02 16:14:48Jitai Hao, Ke Yang, Qiang Huang, Jun YuAbstract
Streaming video understanding is a critical capability for real-world applications, including embodied intelligence, autonomous driving, industrial monitoring, surveillance and early warning, and wearable assistants. However, processing continuous video streams with multimodal large language models (MLLMs) is computationally expensive. Existing efforts have explored reducing streaming overhead through visual token pruning, token merging, quantization, on-demand frame retrieval, and context offloading. However, most existing methods overlook the dimension of model depth. Repeatedly executing full-depth MLLM prefill over incoming frames is prohibitively expensive, incurring substantial computational overhead and causing the KV cache to grow at a rate directly proportional to the prefill depth. To address these challenges, we propose ShallowStream, a novel framework that leverages the shallow layers of an MLLM to simultaneously perform frame encoding and retrieval index building. During stream processing, ShallowStream maintains an always-on lightweight index using the KV cache of shallow layers. During query-time answering, we leverage the attention scores generated by the shallow layers to score context frames and employ a diversity-aware selection strategy to retrieve precise and comprehensive evidence. ShallowStream achieves performance on par with the strongest existing streaming methods, while reducing per-frame prefill latency and 10-second end-to-end latency by up to 52.1x and 11.9x, respectively. Our code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.02780
PDF
