Zero-Shot
-
ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Device
2026-07-09 17:59:58Fabio Tosi, Luca Bartolomei, Matteo Poggi, Stefano MattocciaAbstract
Monocular depth estimation has seen remarkable progress through foundation models achieving robust zero-shot generalization, yet their computational demands place them far beyond the reach of embedded and mobile platforms. Lightweight alternatives exist, but have been developed almost exclusively within single-domain, self-supervised paradigms, failing silently under domain shift. We present ZipDepth, a compact monocular depth network that bridges this gap by combining an efficient reparameterizable encoder-decoder with large-scale knowledge distillation from a foundation model over a large multi-domain training set. Comprising just 6.1M parameters, ZipDepth runs at real-time rates from server GPUs to power-constrained devices, achieving the best trade-off between zero-shot accuracy and deployment efficiency among lightweight models across five benchmarks, taking a significant step towards the accuracy of foundation models with 50x more parameters.
Abstract (translated)
URL
https://arxiv.org/abs/2607.08771
PDF
-
LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models
2026-07-09 17:59:52Cheng-De Fan, Chun-Wei Tuan Mu, Chen-Wei Chang, Chin-Yang Lin, Kun-Ru Wu, Yu-Chee Tseng, Yu-Lun LiuAbstract
Recovering high-quality video from sparse event streams is a challenging task. Regression methods often blur textures, while existing generative models struggle with long-term stability. We propose LongE2V, a novel approach that leverages pre-trained video diffusion priors to jointly handle event-based video reconstruction, prediction, and frame interpolation. By fine-tuning a foundational video model, our approach achieves high data efficiency and superior perceptual quality. We introduce Autoregressive Unrolling and Adaptive Context Switching to mitigate temporal drift in extremely long sequences. We also propose Reencoding Alignment with Cross Residual Correction to ensure precise bidirectional consistency during frame interpolation. Furthermore, Event Voxel Density Augmentation ensures robustness across varying sensor resolutions. Extensive experiments on real-world benchmarks demonstrate that LongE2V outperforms state-of-the-art methods across all three tasks, exhibiting exceptional temporal coherence and zero-shot generalization. Project page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2607.08770
PDF
-
HumanForge: A Human-Centric Deepfake Video Benchmark with Multi-Agent Forgery Rationales
2026-07-09 17:12:41Wenbo Xu, Zhimin Chen, Xiaojie Liang, Hengrui Liu, Wei LuAbstract
Rapid advancements in video diffusion models and temporal editing tools have enabled the generation of highly realistic human-centric videos, posing unprecedented challenges to digital content forensics. Existing benchmarks primarily focus on either face-swapping or global text-to-video synthesis, overlooking the crucial dimensions of human-object or human-human interactions and multi-modal alignment. To address these limitations, we introduce HumanForge, a unified, large-scale, and multi-paradigm human-centric video forgery dataset. To construct and annotate this dataset without labor-intensive manual labeling or hallucinated monolithic prompts, we propose Gen2Anno, a modular active multi-agent pipeline built on LangGraph. Gen2Anno coordinates six specialized agents-ranging from source profiling to MoE-based reference analysis and closed-loop forensic verification-to generate over 18K high-fidelity video segments and produce structured, contrastive omni-annotations containing binary decisions, fine-grained artifact categories, and spatio-temporal localization. Extensive benchmarks using state-of-the-art traditional detectors and Large Multimodal Models (LMMs) demonstrate the significant challenges of zero-shot generalization and fine-grained reasoning on HumanForge. Code and dataset will be publicly released.
Abstract (translated)
URL
https://arxiv.org/abs/2607.08705
PDF
-
Improving Ad-hoc Search Effectiveness for Conversational Information Retrieval via Model Merging
Abstract
Conversational information retrieval is challenging since it requires the consideration of the conversation history which potentially gives rise to topic shifts and coreference resolution across previous turns. To address these challenges, previous work mainly rely on traditional fine-tuning of ad-hoc retrievers on conversational datasets or extrapolates their generalizability through multi-tasking. However, this mainstream approach is costly - since it requires model re-training - and exhibits catastrophic forgetting, where the model loses its foundational ad-hoc retrieval performance. In this paper, we fill this gap by introducing model merging as a training-free strategy enabling the design of a single retrieval model that operates across both ad-hoc and conversational settings with no additional fine-tuning. We conduct experiments using linear and non-linear parameter-wise merging strategies - namely Model Soup and Slerp - on standard ad-hoc search and conversational retrieval datasets. Our results demonstrate that model merging significantly enhances the ad-hoc search capabilities of conversational retrievers while improving generalizability across task-specific datasets, achieving up to 15% higher NDCG@3 under zero-shot conditions.
Abstract (translated)
URL
https://arxiv.org/abs/2607.08540
PDF
-
Best-of-$N$ TTS Evaluation is Confounded by ASR Family Alignment
2026-07-09 09:01:03Taehyung Yu, Seongjae KangAbstract
Best-of-$N$ (BoN) inference improves content consistency in zero-shot text-to-speech by selecting from $N$ candidates with an automatic speech recognition (ASR) verifier. We identify an underexplored evaluation confound: a verifier's apparent quality depends strongly on which ASR family judges it. On LibriSpeech-PC test-clean~\citep{librispeechpc} with F5-TTS~\citep{f5tts}, verifier rankings reverse across Whisper, wav2vec~2.0, and HuBERT evaluators, and same-family verifier-evaluator pairs recover 2-3$\times$ more oracle headroom than cross-family pairs despite near-identical representations (linear CKA $0.978$) -- a pattern consistent with identity- or lineage-level coupling rather than representational overlap. We propose two \textbf{cross-family rank ensembles} (rank-averaging and conjunctive max-rank) that attain the lowest mean WER across three independent evaluators -- $1.61\%$ at $N{=}10$ ($-12\%$ relative to F5-TTS) -- with no measurable degradation under automatic SIM-o/UTMOS metrics; the best single verifier drives WER from $2.06\%$ to $1.72\%$ ($-16.5\%$) under the official F5-TTS evaluator. We recommend cross-evaluator triangulation as default reporting practice.
Abstract (translated)
URL
https://arxiv.org/abs/2607.08256
PDF
-
ICDAR 2026 HIPE-OCRepair Competition on LLM-Assisted OCR Post-Correction for Historical Documents
2026-07-09 06:26:13Maud Ehrmann, Emanuela Boros, Juri Opitz, Andrianos Michail, Florian Wagner, Simon ClematideAbstract
We present the results of HIPE-OCRepair-2026, an ICDAR competition on LLM-assisted OCR post-correction of historical documents. OCR post-correction remains a long-standing challenge in digital heritage: large-scale collections of digitized documents are affected by legacy OCR errors, while re-digitization at scale remains impractical. Large language models (LLMs) offers a major opportunity to revisit this challenge, yet their effectiveness across languages, document types, and noise conditions - and their tendency to hallucinate - remains insufficiently understood. HIPE-OCRepair-2026 pursues two objectives: (i) to evaluate the capabilities of modern OCR post-correction systems, and (ii) to provide a reproducible evaluation framework anchored in the HIPE-OCRepair-2026 dataset, a harmonized multilingual resource consolidating existing and newly curated historical datasets. Participants were tasked with correcting noisy OCR transcripts from historical newspapers and printed works in English, French, and German (17th-20th century), working at the level of coherent transcription units (paragraphs or articles) without access to source images. The evaluation adopts a retrieval-oriented rather than diplomatic scoring approach, reflecting the practical use case of search and access over digitized collections. Four teams submitted systems ranging from zero-shot prompting to continued pre-training and fine-tuning, offering insights into the merits of different adaptation strategies. Results show that modern LLM-assisted systems can significantly improve OCR quality, but performance varies across datasets, languages, and noise levels. Over-correction on low-noise inputs emerges as a recurring challenge, highlighting the importance of evaluation beyond character error reduction. The dataset, scorer, and evaluation pipeline are publicly released to support future research.
Abstract (translated)
URL
https://arxiv.org/abs/2607.08143
PDF
-
MASTE: A Multi-Agent Pipeline for Zero-Shot Aspect Sentiment Triplet Extraction
2026-07-09 03:20:54Ao Hong, Lehang Wang, Zhirun Yue, Mingxin Wang, Zihan Wang, Houde LiuAbstract
Aspect Sentiment Triplet Extraction (ASTE) requires jointly identifying (aspect, opinion, sentiment) triples from a given review sentence. While large language models (LLMs) achieve strong zero-shot performance on many NLP benchmarks, their effectiveness on ASTE remains limited, as single-pass generation forces the model to determine span boundaries, opinion grouping, and sentiment polarity in a single decoding step. Common remedies, such as few-shot in-context learning and chain-of-thought prompting, offer only marginal improvements and rely heavily on either in-domain demonstrations sampled from labeled training data or carefully engineered reasoning prompts, neither of which is broadly available in zero-shot deployment. Inspired by the classical agent paradigm, we propose MASTE, a multi-agent pipeline for zero-shot Aspect Sentiment Triplet Extraction. MASTE decomposes ASTE into four sequential stages, where specialized agents handle different compositional subtasks with explicit conditioning on prior outputs. This design enables entirely training-free zero-shot ASTE and generalizes across different backbones and datasets. Extensive experiments on four ASTE benchmarks show that MASTE substantially outperforms zero-shot and chain-of-thought LLM baselines under the same backbone, narrowing the gap to fully supervised methods without using any labeled triplets. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.08080
PDF
-
Shift & Drift: A Zero-Shot Benchmark for Generalizable and Robust Autonomous Driving Motion Planning
2026-07-08 18:23:48Alessandro Canevaro, Hang Yu, Julian Schmidt, Peizheng Li, Silvan Lindner, Wilhelm Stork, Georg Martius, Julian JordanAbstract
While closed-loop motion planners trained on large-scale, object-level datasets, e.g., nuPlan, demonstrate strong in-distribution (ID) performance, their generalization to novel urban topologies and recovery mechanisms following execution perturbations remain under-explored. To address this, we present Shift & Drift, a novel dual-track benchmark designed to rigorously stress-test motion planners across two critical axes of distribution shift: (1) The Semantic Shift Track leverages a novel conversion pipeline that transforms the aerial, DeepScenario Open 3D dataset into the nuPlan simulation framework. This enables zero-shot evaluation of planners trained on North American and Singaporean data against 1,182 scenarios spanning four German cities and the US city of San Francisco featuring dense pedestrian-cyclist interactions. (2) The State-Distribution Drift Track injects stochastic perturbations into the ego vehicle's dynamics to quantify robustness against compounding execution errors. Based on this, we systematically evaluate the failure modes of diverse planning paradigms under semantic and state-distribution shifts. While imitation learning methods achieve high scores in ID benchmarks, they exhibit significant failures under semantic shift, particularly in pedestrian-dense environments, and suffer from persistent drift when subjected to temporally correlated actuation noise. In contrast, the evaluated reinforcement-learning-based planner demonstrates more graceful degradation, maintaining higher safety and progress metrics across both tracks. Our findings reveal an empirical trade-off between imitation fidelity and closed-loop resilience, providing the community with a rigorous benchmark to evaluate progress toward reliable deployment.
Abstract (translated)
URL
https://arxiv.org/abs/2607.07844
PDF
-
MedPMC: A Systematic Framework for Scaling High-Fidelity Medical Multimodal Data for Foundation Models
2026-07-08 17:26:49Hyunjae Kim, Dain Kim, Pan Xiao, Serina S. Applebaum, Younjoon Chung, Xuguang Ai, Yu Yin, Roy Jiang, Yuexi Du, Yawen Wei, Yiming Kong, Tuo Guo, Zhiyuan Cao, Mengmeng Du, Yuelei Fu, Yan Hu, Rui Shi, Gui Yang, Kevin W. Jin, Yuntian Liu, Yuxuan Tian, Jonathan Marquez, Zhen Chen, Sheng Zhang, Hoifung Poon, Hua Xu, Jaewoo Kang, Qingyu ChenAbstract
Medicine is inherently multimodal, requiring clinicians to synthesize information across diverse data streams. Yet the development of multimodal foundation models is constrained by limited access to large-scale, high-quality clinical data. Although PubMed Central (PMC) offers a complementary source of expert-authored image-text data, existing PMC-derived resources remain limited in fidelity, reproducibility, and clinical validation. We introduce MedPMC, an automated, continuously updatable framework that transforms permissively licensed literature into high-fidelity infrastructure for medical multimodal models. Applied to 6.1 million PMC articles, MedPMC curated 11 million medical image-text pairs. Component evaluations showed strong performance for initial screening (F1 = 93.2), multi-panel figure detection (F1 = 96.5), figure separation (mAP = 89.8), caption separation and alignment (F1 = 81.4; ROUGE-L = 85.3), and medical figure classification (F1 = 96.5). Manual review by five annotators, three with medical training, found 95.3% of MedPMC images medically relevant, versus 19.7% in a prior PMC-derived dataset. Across 26 benchmarks spanning 11 specialties, a MedPMC-trained CLIP-style model improved average zero-shot AUC by 7.1 percentage points over the strongest architecture-matched biomedical CLIP baseline despite using fewer than half as many image-text pairs. As the vision encoder in a multimodal large language model, it improved medical visual question-answering by 1.9 and 16.9 percentage points across two benchmarks. In 10,524 Yale New Haven Health System dermatology photographs, it improved morphology-to-image retrieval Recall@5 by 11.7 percentage points. These findings show that high-fidelity literature curation strengthens medical multimodal foundation models across benchmark and clinical settings. We publicly release the framework, corpus, benchmarks, and pretrained models.
Abstract (translated)
URL
https://arxiv.org/abs/2607.07673
PDF
-
Context-Aware Force Estimation for Deformable Tool Manipulation in Robotic Environmental Swabbing via Few-Shot Continual Adaptation
2026-07-08 16:01:23Siavash Mahmoudi, Chaitainya Kuppar Reddy, Yang Tian, Dongyi WangAbstract
Robotic surface swabbing requires sustained interaction between a compliant tool and heterogeneous environments, where accurate estimation of tip-level contact force is critical for consistent sampling performance. However, deformable tool dynamics introduce nonlinear viscoelastic hysteresis that decouples wrist-mounted force measurements from true contact forces, while tool-integrated sensors are impractical for deployment due to sterility and disposability constraints. This paper presents a data-driven framework for contact force estimation in Deformable Tool Manipulation (DTM) that leverages proprioceptive sensing without requiring explicit physical models or permanent embedded sensing hardware at the tool tip. A recurrent architecture is first identified through a comparative evaluation of temporal models, where a compact LSTM achieves the lowest estimation error and sub-millisecond inference latency. To address generalization across unseen surfaces and tool compliance conditions, we introduce a parameter-isolated few-shot adaptation strategy that augments a frozen recurrent backbone with low-dimensional context embeddings using feature-wise linear modulation (FiLM). Experiments on a UR5e platform across nine tool-surface interaction regimes demonstrate that the proposed approach significantly improves robustness under domain shift, reducing zero-shot estimation error by up to 63\% while preserving baseline performance without catastrophic forgetting. These results show that separating shared deformation-history dynamics from domain-specific conditioning enables reliable force estimation for DTM in non-stationary environments.
Abstract (translated)
URL
https://arxiv.org/abs/2607.07574
PDF
-
When Prompts Ignore Structure: Graph-Based Attribute Reasoning for Calibrated VLMs
2026-07-08 13:31:17Tanay Sodha, Aditya Sharma, Ramya Hebbalaguppe, Vinti Agarwal, Pranav Murthy YeluripatyAbstract
Reliable confidence estimation remains a key limitation of test-time adaptation in vision-language models (VLMs), where prompt tuning improves zero-shot accuracy but often degrades calibration due to entropy-driven overconfidence. Prior approaches mitigate this using LLM-derived class attributes and contrastive regularization, yet treat attributes independently, ignoring their relational structure. We propose ARGTCA, which represents (class, attribute) pairs as nodes in a Symbolic Attribute Graph and trains a Graph Attention Network (GAT) using contrastive objectives to produce structurally informed embeddings that capture inter-attribute dependencies. We introduce two attribute selection strategies: ARGTCA-DIV for intra-class diversity and ARGTCA-DISC for inter-class discrimination. Experiments across nine benchmarks show that ARGTCA-DIV reduces average Expected Calibration Error (ECE) by approximately ~37% over baselines, while ARGTCA-DISC consistently performs as the second-best variant, reducing average ECE by approximately ~17% over baselines. These results suggest that modeling symbolic attribute interactions provides a principled approach for reliable test-time adaptation in VLMs.
Abstract (translated)
URL
https://arxiv.org/abs/2607.07395
PDF
-
Behavior Foundations for Quadruped Robots: ABot-C0 Technical Report
2026-07-08 13:04:07Xufeng Zhao, Fuzhi Yang, Jianhui Chen, Li Gao, Zhang Meng, Jie Gao, Yao Zheng, Wenyu Liu, Menglin Yang, Minqi Gu, Yaru Zhao, Honglin Han, Shihui Su, Zixiao Tang, Liu Liu, Mu Xu, Yang Cai, Wenbin TangAbstract
In embodied intelligence systems, the motion controller serves as the critical bridge between semantic reasoning and physical execution. Humanoid control has progressed rapidly through large-scale human motion-capture data and motion-tracking paradigm. However, producing quadruped robots motion corpora with scalability and physical feasibility faces more fundamental obstacles: animal motion data is scarce, and cross-embodiment retargeting remains fragile. We present ABot-C0, a generalist motion-control system for quadruped robots that establishes three complementary behavior foundations: a scalable multi-source motion-data pipeline, robust policy learning across motion tracking, locomotion, and scene interaction, and a unified deployment stack for reliable real-world operation. Fundamentally, we construct a data pyramid through conditional video-generation synthesis, annotated motion capture, teleoperation and human design, producing 16,074 physically feasible motion clips as the data foundation for various motion learning demands. We then train a Flow-Matching generalist policy that demonstrates for the first time quadruped motion tracking scaling law that its performance improves consistently as training scales up, with zero-shot capability to track unseen motions. Then, we push a step further for robust all-terrain traversal locomotion by adopting a three-stage privileged-to-perceptive framework with temporal LiDAR memory and terrain-predictive supervision. Collectively, these components form a motion generalist that coordinates multi-policy execution, smooth behavior transitions, energy-efficient control, and safety mechanisms for real-world deployment. Extensive experiments on urban-terrain autonomous navigation and companion-style multimodal interaction demonstrate that quadruped robots move beyond single-function demos toward product-level behavioral intelligence.
Abstract (translated)
URL
https://arxiv.org/abs/2607.07370
PDF
-
HAJJv2-CrowdCount: Zero-Shot Benchmark for Dense Crowd Counting
2026-07-08 12:11:57Reem AlYabis, Fares AlTuwaim, AlJawharh AlOtaibi, Mohamed EltahirAbstract
Automated crowd counting in Hajj video is difficult not because current models lack capacity, but because the footage violates the assumptions those models were built on: cameras observe the crowd from steep, near-vertical angles, individuals occlude one another extensively, and a single frame can contain well over a thousand people. Benchmarks that test crowd counting in such an environment are either private or not detailed per second. We revisit the HAJJv2 dataset and contribute HAJJv2-CrowdCount: per-second human-annotated crowd counts for its testing videos. Using these annotations, we benchmark three recent zero-shot counting paradigms: an open-vocabulary detector (YOLO-World), a point-based counter (APGCC), and a promptable segmentation-based counter (SAM3Count). SAM3Count attains the lowest overall mean absolute error (MAE 70.4, 95% CI 56.0-86.1), ahead of YOLO-World (92.0) and APGCC (152.9). This ordering reverses, however, in the regime most relevant to deployment: on the densest frames, the detection- and segmentation-based counters both degrade sharply (MAE exceeding 300), while the point-based counter degrades far more gracefully (MAE 114.9). This inversion is decision-relevant for Hajj crowd management, where reliable counts are needed most precisely in the densest and most occluded scenes. The annotations are released to support reproduction and extension of these results.
Abstract (translated)
URL
https://arxiv.org/abs/2607.07322
PDF
-
Prototype-Anchored Generalized Manifold Regression for Unknown-Domain Object Detection
2026-07-08 09:27:15Zihao Zhang, Aming Wu, Yang Li, Yahong HanAbstract
In this paper, we study Single-Domain Generalized Object Detection (Single-DGOD), which aims to transfer a detector trained on a single source domain to multiple unseen domains. Existing methods mainly rely on simulation-driven strategies, such as data augmentation or textual prompts, to enlarge the training distribution. However, finite simulations can hardly cover the dynamic variations of real-world scenarios, often causing overfitting to synthetic styles and limited robustness to complex structural degradations. Inspired by the manifold hypothesis, we argue that semantic features, despite diverse visual changes, should lie on a compact and stable low-dimensional manifold. Therefore, robust generalization requires rectifying deviant samples back to this semantic manifold, rather than exhaustively simulating external perturbations. To this end, we propose Manifold Regression with Visual-Text Dual Chain-of-Thought (MR-DCoT), which formulates unknown-domain generalization as a manifold regression problem. MR-DCoT first uses a Visual-Text Dual Chain-of-Thought module to combine VLM-guided semantic evolution with diffusion-based structural perturbation, generating structured off-manifold hard examples. It then introduces Class-Specific Prototype Anchoring to learn a rectification operator that projects deviant features toward the source semantic manifold. By integrating outlier generation and semantic correction into a closed loop, MR-DCoT effectively narrows the distribution gap and improves robustness under unseen shifts. Extensive experiments on three complementary benchmarks, including adverse-weather detection, real-to-art generalization, and zero-shot semantic segmentation, demonstrate the effectiveness and versatility of our method.
Abstract (translated)
URL
https://arxiv.org/abs/2607.07192
PDF
-
Comparative Study of Domain-adapted VLMs for General Document Visual Question Answering
2026-07-08 09:13:59Miguel Lopez-Duran, Elena Marrero, Julian Fierrez, Marta Robledo-Moreno, Ruben Vera-Rodriguez, Daniel DeAlcala, Aythami Morales, Ruben Tolosana, Oscar Delgado, Alvaro Ortigosa, Javier Ortega-GarciaAbstract
Document Visual Question Answering (DocVQA) presents a complex multimodal challenge, requiring models to exploit visual, textual, and layout information from documents. Although Vision-Language Models (VLMs) have shown remarkable performance in text-vision tasks, their robustness and transferability to different document domains remains underexplored. In this study, we present a comprehensive evaluation of 8 open-source pretrained VLMs on DocVQA in three different document domains: industrial documents of varying type, infographics, and presentation slides. We systematically assess model performance under zero-shot evaluations, fully supervised finetuning with inter- and intra-dataset evaluations, and few-shot learning evaluations of knowledge transfer between domains. Our findings demonstrate that while large pretrained VLMs possess strong zero-shot baselines for structured layouts, their performance strongly decreases on visually complex layouts of infographics and slides. Although parameter scaling is a dominant factor on performance, supervised finetuning yields higher relative gains in smaller architectures. Furthermore, our cross-domain and few-shot experiments show that visual understanding is the main bottleneck for DocVQA, not a lack of knowledge from the VLMs. Using 50 target domain samples, the models finetuned in DocVQA with datasets of different domains rapidly adapt to the target domain documents, even surpassing their fully supervised counterparts in some cases.
Abstract (translated)
URL
https://arxiv.org/abs/2607.07179
PDF
-
Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE
2026-07-08 06:23:42Haozhan Tang, Zerui Wang, Yuxian Gu, Song Han, Han CaiAbstract
Modern LLMs are increasingly deployed in long-context applications such as retrieval-augmented generation, repository-level coding, and agentic workflows whose accumulated reasoning and tool traces routinely push the input an order of magnitude past the pretraining window, making zero-shot context extension the dominant deployment path for open-weight checkpoints. Most existing zero-shot methods fix a single rescaling factor up front, so an aggressive factor sacrifices short-context fidelity while a conservative one breaks down at long contexts. We propose Jet-Long, a tuning-free zero-shot method that pairs a local RoPE-faithful window with a long-range window whose rescaling factor adapts dynamically to the current sequence length, recovering the base model exactly at short inputs while extrapolating cleanly at long ones. An inclusion-exclusion attention merge and an on-the-fly RoPE correction rotation make the bifocal construction essentially free at inference; fused into a single CuTe kernel, long-context prefill reaches up to $1.39\times$ FA2 throughput on H100 (approaching the Hopper-only FA4), and single-batch generation incurs $\le 4\%$ overhead at every length. On Qwen3-1.7B/4B/8B up to 128K context, Jet-Long leads RULER by $+4.79$/$+2.18$/$+2.03$~pp over the strongest baseline at 1.7B/4B/8B, achieves the best overall accuracy on HELMET-RAG (a benchmark identified by HELMET as the most efficient predictor of downstream long-context performance) and attains the lowest PG-19 perplexity. Jet-Long also generalizes to hybrid attention architectures such as Jet-Nemotron for further long-context improvement without retraining, and remains hyperparameter-resilient for ease of deployment.
Abstract (translated)
URL
https://arxiv.org/abs/2607.07740
PDF
-
Large Behavior Model: A Promptable Digital Twin of the Retail Customer
2026-07-08 04:31:18Wachiravit Modecrua, Krittin Pachtrachai, Touchapon KraisingkornAbstract
Customer behavior modeling underpins recommendation, marketing, and decision support, yet existing approaches either optimize predictive accuracy without explaining decisions or simulate users without grounding them in real behavioral data. We present the Large Behavioral Model (LBM) that learns customer decision making directly from large-scale retail transactions through a unified Person-Environment formulation. Customer state is represented by a behavioral profile derived from historical purchases, while product context is incorporated through retrieval-augmented generation. The model is trained using continued pre-training on verbalized behavioral data, supervised fine-tuning for decision generation, and reinforcement learning with verifiable rewards for evidence-based calibration. We evaluate the proposed framework on purchase prediction, hard-negative discrimination, basket completion, promotion response, and cross-domain voucher redemption. The model consistently outperforms frontier general-purpose language models on in-domain retail tasks while demonstrating strong zero-shot and fine-tuned transfer across retailers and decision domains. Ablation studies show that continued pre-training is the primary driver of behavioral generalization, retrieval is most effective when applied during both training and inference, and reinforcement learning improves reliance on explicit behavioral evidence over generic language-model priors. These results demonstrate that behavioral knowledge encoded in transaction histories can be effectively learned by language models, providing a scalable foundation for customer digital twins and behavior simulation.
Abstract (translated)
URL
https://arxiv.org/abs/2607.06993
PDF
-
MMGenre: Benchmarking Singing Voice Synthesis across Multiple Musical Genres
Abstract
Singing voice synthesis (SVS) has progressed rapidly, yet its ability to generalize across diverse musical genres remains underexplored. Existing benchmarks are heavily biased toward pop music, limiting systematic analysis of genre-dependent behavior. We introduce MMGenre, a benchmark for multi-genre SVS diagnosis, supported by an automatic pipeline for constructing genre-aligned music scores. MMGenre spans 10 major genres and 26 subgenres, enabling comprehensive analysis of genre-aware synthesis. Extensive evaluation of representative SVS models reveals limited genre discrimination: synthesized vocals across genres exhibit highly similar acoustic characteristics and weak separability. While zero-shot genre adaptation yields only marginal improvements, lightweight genre-specific continued training leads to substantial gains. MMGenre provides a standardized framework for multi-genre SVS evaluation and exposes critical challenges in achieving genre-aware singing voice synthesis.
Abstract (translated)
URL
https://arxiv.org/abs/2607.06986
PDF
-
GemNav: Discrete-Token Visual Robot Navigation using a Multimodal Large Language Model
2026-07-08 00:46:57Peter Bohm, Saimunur Rahman, Abdelwahed Khamis, Sagun Man Singh Shrestha, Chris McCool, Peyman MoghadamAbstract
Visual navigation policies built on large pretrained models have so far followed a common recipe: a dedicated visual encoder, a bespoke action head, and training on thousands of hours of cross-embodiment datasets. We ask whether this recipe is necessary. In this paper, we introduce GemNav, a visual robot navigation policy that adapts a frozen Multimodal Large Language Model (MLLM) for short-to-medium horizon waypoint navigation using Low-Rank Adaptation (LoRA) on the language tower alone, with no auxiliary visual encoder and no continuous regression head. Waypoints and categorical navigation signals share a single discrete token vocabulary generated by the language-model head, and a soft-decoded auxiliary loss recovers the metric structure that pure cross-entropy training discards. On a single 8.7-hour open corpus, roughly three orders of magnitude smaller than competing training sets, the policy transfers zero-shot to four physically distinct unseen environments and stops within 0.25-0.42m of the goal across 20 real-world trials covering an open carpark, an obstacle carpark, a long outdoor chemical yard, and an indoor warehouse. Conditioning on short image histories improves offline metrics but yields no robot benefit, pointing to a ceiling on what temporal context adds once pretrained vision features are in place. These results indicate that discrete-token adaptation of frozen MLLMs can provide a data-efficient, deployable alternative for foundation model robot navigation.
Abstract (translated)
URL
https://arxiv.org/abs/2607.06882
PDF
-
Video2Reaction: Mapping Video to Audience Reaction Distribution in the Wild
2026-07-08 00:17:20Trang Nguyen, Sidong Zhang, Shiv Shankar, Gauri Jagatap, Deepak Chandran, Andrea Fanelli, Madalina FiterauAbstract
Understanding and forecasting audience reactions to video content are crucial for improving content creation, recommendation systems, and media analysis. To enable audience reaction prediction and other content engagement applications, we introduce $\textbf{Video2Reaction}$, a multimodal dataset that maps short movie segments to a distribution of $\textit{induced emotions}$ of viewers in the wild, as expressed through social media. $\textbf{Video2Reaction}$ spans more than 10,000 videos and serves as a reliable benchmark as well as a training resource for audience reaction prediction. To enable cost-effective continuous annotations as reactions may change over time, we develop a two-stage multi-agent pipeline using only open-source LLMs, achieving 86% correctness under blind human verification despite the inherently noisy and subjective nature of the task. We establish the first benchmark for video-to-reaction-distribution prediction in the wild and show that pretrained foundation video models fail in zero-shot settings, while finetuning transforms them into state-of-the-art predictors capable of modeling both full reaction distributions and dominant responses from video alone. However, the task remains challenging: even the strongest methods achieve only 77% Top-3 F1 in dominant reaction prediction (LLaVA-Next), highlighting a substantial gap in modeling collective audience reaction. \modification{Dataset and code are available at our project page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2607.06875
PDF
