SeqLoRA introduces a bilevel optimization framework for continual learning of text‑to‑image diffusion models, jointly optimizing LoRA factors while enforcing orthogonality between new and existing concept bases. The method achieves monotone descent, convergence guarantees, and a high‑probability bound on catastrophic forgetting that depends on residual interference energy. Experiments on Stable Diffusion with up to 101 concepts demonstrate improved identity preservation, minimal cross‑concept leakage, no need for a fusion step, and scalability beyond memory limits of fusion‑based approaches.
By Javad Parsa, Enis Simsar, Amir Joudaki, Thomas Hofmann, Andr\'e M. H. Teixeira
GPEC is a lightweight pre‑LLM Gaussian Process Embedding Correction that refines visual representations for cardiac ultrasound caption generation. By inserting a residual correction layer between the visual projection and the language model, it aligns projected embeddings with annotation‑guided targets derived from structured video annotations. Experiments show that GPEC improves caption similarity and content alignment while adding less than 0.05 s of inference overhead, all without fine‑tuning the pretrained multimodal backbone.
By Arefeh Rezaei
The paper introduces a prototype‑based fuzzy‑rule framework that interprets patch‑level features from pretrained foundation models without fine‑tuning. By clustering class‑specific prototypes in the feature space, the method translates latent representations into human‑readable IF‑THEN rules, achieving accuracy comparable to black‑box classifiers on gastrointestinal imaging tasks. The extracted rules are also used to analyze synthetic medical images, revealing where generators diverge from real tissue.
By Michael D. Vasilakakis (Department of Computer Science and Biomedical Informatics, University of Thessaly, Lamia, Greece), Dimitris K. Iakovidis (Department of Computer Science and Biomedical Informatics, University of Thessaly, Lamia, Greece)
The paper introduces Align Then Reason (ATR), a multilingual lip‑sync judge that aligns frame‑level lip representations with phonetic units of a candidate text line and then uses a language model to evaluate both content and timing. ATR achieves significant improvements over existing baselines on a seven‑language benchmark, with mean AUC gains of up to 59.4% for 2B reasoners and similar gains across other LLM families. The method also transfers well to unseen languages and outperforms lip‑reading baselines on real dubbing tasks such as dub‑line reranking and script‑to‑clip assignment.
By Rui Liu, Bhavin Jawade, Haoqi Li, Shivam Mehta, Karan Saxena, Yinghong Lan, Cameron R. Wolfe
The paper presents a framework for creating a scalable synthetic dataset of controllable video interactions by generating explicit start and end state images using image editing models. It introduces State‑Guided Sampling (SGS) to produce seamless videos anchored on these states, reducing artifacts seen in naive conditional generation. An automated evaluation system aligned with human judgments is also developed, and experiments demonstrate that fine‑tuning a base model on this dataset markedly improves its ability to generate plausible interactions.
By Jiho Jang, Jinyoung Kim, Nojun Kwak, Kyungjune Kim
Dyna3 is a training‑free framework that extends the depth foundation model DA3 to perform 4D dynamic scene reconstruction without fine‑tuning. By leveraging DA3’s cross‑view features and a best‑match search, it distinguishes static surfaces from moving objects, and uses vision‑language models to generate semantic prompts for SAM 3 to achieve precise instance‑level segmentation. Experiments on four datasets show Dyna3 outperforms correspondence‑trained methods, improving dynamic object segmentation by +5.5 pp, speeding pose estimation 13×, and reducing memory usage 4–8×.
By Xinhao Xiang, Weiyang Li, Zhijie Zheng, Abhijeet Rastogi, Jiawei Zhang
PAGER is a label‑free adaptation method that aligns partial, viewpoint‑dependent 3D observations with a frozen global semantic space. It uses matched‑point feature alignment and relational supervision to anchor partial features to their global counterparts while preserving similarity structure, all without altering the pretrained encoder or global probe. Experiments show PAGER outperforms label‑supervised PEFT on Sonata and Concerto, and achieves superior zero‑shot transfer from ScanNet to ScanNet++ compared to fully fine‑tuned Sonata.
By Akira-Miranda Adeyomi Adeniran-Lowe, Binod Singh, Lars Arnold Dethlefsen, Lazaros Nalpantidis, Theodora Kontogianni
The paper introduces MOSAIC, a method for personalized federated vision‑language models that addresses domain heterogeneity by focusing on class‑specific cross‑domain residuals. It constructs a decision‑aware harmfulness score to identify residuals that hurt image‑text decision margins, then uses a low‑rank residual adapter with shared class factors and private domain factors, an image‑conditioned gate, and harmful‑pair‑aware reweighting to refine local updates. Experiments on Office31, OfficeHome, and DomainNet100 show consistent improvements in macro‑client top‑1 accuracy across various domain‑shift scenarios.
By Wentao Yue, Qingyu Mao, Tianyou Lai, Ahmed M. Abdelmoniem, Qilei Li
The paper introduces Disentangled Diffusion Autoencoders (DiDAE), a method that wraps a frozen foundation model with a conditional diffusion decoder to generate counterfactual edits along disentangled dictionary directions. DiDAE can use supervised or unsupervised dictionaries, requires no gradients, and is up to 2000 times faster than existing approaches. Evaluations on six datasets show that its counterfactuals match or surpass state‑of‑the‑art methods and can repair downstream classifiers via Counterfactual Knowledge Distillation, with the entire workflow available as an open‑source library.
By Sidney Bender, Benedikt Kunz, Ahmed Zeid, Shinichi Nakajima, Klaus-Robert M\"uller, Marco Morik
SR‑Ground is a large‑scale dataset created to enable fine‑grained segmentation of visual artifacts in super‑resolved images. It contains 63,000 images processed by various state‑of‑the‑art SR models, each annotated at the pixel level for six distinct artifact types, validated through a crowdsourcing study with 1,062 participants. The dataset improves the training of image quality assessment models with grounding capabilities and supports a fine‑tuning pipeline that reduces perceptible artifacts in SR outputs, outperforming no‑reference methods on both benchmark and real‑world low‑resolution datasets.
By Artem Borisov, Evgeney Bogatyrev, Khaled Abud, Dmitriy Vatolin
ChainLoRA is a replay‑free continual learning framework for large language models that merges task vectors while preserving geometry. It uses chain‑updated training with a one‑sided orthogonality proxy to keep historical state and regularization overhead constant, and applies post‑stream adaptive SVD merging with Procrustes adaptation to separate shared and task‑specific components. Experiments demonstrate state‑of‑the‑art performance on Large and SuperNI benchmarks and competitive results on Standard CL, approaching the scores of replay‑based methods.
By Hang Yin, Haozhe Wang, Yuhua Luo, Zhangqi Pan, Xiaoxing Wang, Junchi Yan
VIDA (Visually-Dependent Ambiguity) is a new dataset comprising 2,500 curated instances designed to test whether multimodal machine translation models can use visual input to resolve ambiguous source spans. The authors also introduce Disambiguation-Centric Metrics, which employ an LLM-as-a-judge classifier to verify correct span-level resolution. Experiments with recent large vision‑language models show that visual disambiguation remains difficult, and that chain‑of‑thought supervised fine‑tuning yields stronger out‑of‑distribution performance, especially for collective‑noun ambiguities.
By Jingheng Pan, Xintong Wang, Longyue Wang, Liang Ding, Weihua Luo, Chris Biemann
The paper introduces Langevin-Informed Transfer Learning (LITL), a method that recovers target Langevin dynamics from biased source samples using only black-box feedback. LITL learns the leading spectral structure of the target infinitesimal generator and the projected drift via Dirichlet representation learning, enabling kinetic reconstruction and slow-manifold gradient estimation. The authors provide finite-sample guarantees for eigenvalue, eigenfunction, and drift estimation, and demonstrate LITL’s ability to recover physical transition timescales, build kinetic structure from static generative samples, reconstruct spherical symmetries, and steer latent representations in trained neural networks.
By Vladimir R. Kostic, Karim Lounici, H\'el\`ene Halconruy, Timoth\'ee Devergne, Michele Parrinello, Massimiliano Pontil
The paper investigates the validity of using AI‑learned representations—such as compressed text, images, and other covariates—as controls in causal analysis. It shows that for a wide class of estimands, the bias introduced by imperfect representations is the product of two errors: one in the outcome regression and one in the balancing weight (or Riesz representer). The authors provide three key results: (1) cross‑fitted double machine learning yields valid Wald inference for the representation‑dependent target and can achieve semiparametric efficiency when representation errors are small; (2) fold‑wise representation learning (fine‑tuning) can be combined with DML inference using convex‑ and star‑aggregation pipelines; and (3) when representation errors are large, the framework offers interpretable sensitivity regions and root‑n inference for their endpoints. In a multi‑modal demand study, the approach produced consistent negative near‑unit elasticity estimates across seven representation‑specific models and their star aggregate, remaining robust across the sensitivity grid.
By Andres Aradillas Fernandez, Victor Chernozhukov, Carlos Cinelli, Sven Klaassen, Whitney Newey, Martin Spindler, Jan Teichert-Kluge, Suhas Vijaykumar
The paper introduces TALON, a Task‑Adaptive LoRA‑Teacher framework for Few‑Shot Class‑Incremental Learning. TALON assigns a dedicated LoRA‑Teacher to each incremental task, then distills the frozen teachers into a single LoRA‑Student via Ensemble Knowledge Transfer, using a semantic‑guided weighting scheme to reduce forgetting and overfitting. Experiments on four FSCIL benchmarks show that TALON matches or surpasses state‑of‑the‑art accuracy while using up to 33× fewer deployment parameters and cutting inference time by 41.7%.
By Hongwei Zhao (School of Computer Science,Engineering, Beihang University), Rui Liu (School of Computer Science,Engineering, Beihang University), Yansong Liu (School of Computer Science,Engineering, Beihang University), Zhiyuan Zou (School of Computer Science,Engineering, Beihang University), Yong Chen (School of Computer Science, Beijing University of Posts,Telecommunications)
4DMulti is a physics‑guided learning framework that automates multicomponent identification from large‑scale four‑dimensional scanning transmission electron microscopy data. It leverages a 6‑million‑pattern diffraction database, a retrieval‑conditioned latent diffusion transformer (Sim2real) for realistic pattern generation, and a rotation‑invariant convolutional network for phase classification, achieving 98.82% accuracy on a five‑phase benchmark. The method introduces a diffraction‑inferred structural complexity metric and produces single‑nanometer‑resolution structural maps of complex material interfaces such as superconducting heterostructures, corroded alloys, and degraded solid‑state battery interfaces.
By Haoran Zhang, Zian Mao, Shufen Chu, Xiaoya He, Yuyan Guan, Antong Yang, Mingze Li, Xiaoqin Zeng, Yujun Xie
ContractRL introduces a contract-constrained sequential repair protocol for structured tool calls, modeling verifier-guided JSON repair as a bounded decision process. The policy observes candidate data, verifier feedback, JSON pointers, repair history, and budget, using a contract-derived action mask to filter invalid operations before a deterministic validator applies changes. Compared to Patch‑SFT and full regeneration, ContractRL achieves higher semantic success (0.9362 vs. 0.9076 and 0.9148) while generating fewer tokens (34.4 vs. 44.9 and 137.2), and policy optimization further improves success rates.
By Miaobo Hu, Shuhao Hu, Xiaobo Guo, Xin Wang, Bokun Wang, Yina Sa, Daren Zha, Jun Xiao
FedLore introduces a communication- and memory-efficient federated learning framework that shares a low-rank optimization basis across clients each round, mitigating subspace fragmentation and enabling exact low-rank aggregation. By refreshing this shared basis across rounds, FedLore allows model updates to exceed the per-round rank budget while maintaining a provable $O(T^{-1/2})$ stationarity bound under standard assumptions. Experiments on vision and language tasks, including federated pre‑training, demonstrate that FedLore outperforms low‑rank adapter baselines and matches or surpasses full‑parameter training while reducing communication and optimizer‑state memory.
By Junkang Liu
LineupRL introduces a reinforcement learning framework with verifiable rewards for time series captioning, using a frozen large language model to identify the correct time series from a set of distractors based on a generated caption. This approach bypasses the limitations of supervised fine‑tuning and traditional RL rewards that poorly transfer to open‑ended time series generation. Experiments on two captioning benchmarks, as well as forecasting and reconstruction tasks, show that LineupRL outperforms both SFT and RL baselines across all metrics, and its trained 3B vision‑language model surpasses a 72B model distilled from SFT captions. The method also demonstrates resistance to reward hacking and produces captions that accurately trace trends and name key values.
By Haochen Zhang, Laura Yao, Zachary Plotkin, Gengwei Zhang, Tianlong Chen
The paper surveys recent advances in Retrieval Augmented Generation (RAG), a technique that integrates external retrieval into language model generation to reduce hallucinations and keep knowledge current. It introduces a four‑axis taxonomy—efficiency, defense, interactivity, and reasoning—to organize contemporary RAG research, covering retrieval methods, fusion strategies, embedding optimizations, and reinforcement learning policies. The survey also reviews evaluation practices, domain‑specific applications, and architectural variants, while highlighting ongoing challenges such as retrieval quality, reliability, domain adaptation, scalability, and explainability.
By Meghana Sunil, Shravya V, Shravan Venkatraman, Joe Dhanith PR