The paper introduces DART, a training‑free technique that combines low‑rank coordinate transport with target‑schedule response calibration to improve the reuse of LoRA adapters in few‑step video diffusion models. By using forward evaluations without source training videos, DART enhances joint quality scores and functional retention on a four‑step Wan2.2 target, with calibration contributing most of the gains. Component analysis shows complementary benefits from coordinate transport, and adapter‑level results indicate both positive functional effects and reduced negative transfer across different adapters.
By Shihong Li, Juntao Xu, JinCao, Maowen Tang, Jun Huang, Jintao Li
CliniCIRCA is a modular large‑language‑model framework that reconstructs longitudinal mental‑health patient journeys from raw electronic health record narratives. It temporally classifies clinical events in unstructured discharge summaries without explicit timestamps, producing 15,891 tagged events from 52 summaries and correcting 629 errors to create verified gold‑standard timelines. The framework then generates temporally grounded summaries, compressing each source by 1.52×, and scales to produce 1,000 silver‑standard timelines for training, showing that instruction tuning improves event extraction, temporal tagging, and summarization across models.
By Aiwei Ivy Zhang, Nimra Ishfaq, Mohit Chandra, Santiago Alvarez Lesmes, Adam Coscia, Khatiya Chelidze Moon, Xiaohan Ding, Munmun De Choudhury
The paper investigates an output‑selection bottleneck in frozen DETR‑family segmentation models, showing that many useful mask proposals are computed but never exposed. A lightweight selector called HYDRA, trained only on cached outputs, can recover up to +7.41 mIoU on ADE20k and COCO and +9.4 class‑macro prompt‑IoU on SAM 3 across eight domains by selectively choosing better candidates. The study demonstrates that evaluating segmenters should consider both exposed masks and the hidden candidates they suppress.
By Ignacio M. De la Jara, Cristian Rodriguez-Opazo, Damith Ranasinghe
E-AVI is a new framework for automated video interview assessment that combines verbal, acoustic, and visual data. It extracts timestamped multimodal evidence and uses dimension‑conditioned attention with source‑level embeddings to score candidates. The system also provides a shared evidence pool for natural‑language feedback and follow‑up question answering, outperforming multimodal baselines on RecruitView and a private hospitality dataset.
By Haoshen Wang, Dongbo Che, Zeyi Xie, Yuanjie Du, Shicheng Hua, Xingyu Wang
The paper introduces ActObs, a supervised fine‑tuning method that, unlike standard approaches, also predicts environment observations in agent trajectories. While both ActObs and action‑only training perform similarly after initial fine‑tuning, ActObs diverges during subsequent reinforcement learning, yielding higher pass@k scores on several benchmarks and better cross‑domain task performance. The authors attribute this advantage to ActObs’s joint supervision, which preserves observation gradients and prevents the policy from over‑specializing on actions alone.
By Juzheng Zhang, Disha Makhija, Manoj Ghuhan Arivazhagan, Vinayshekhar Bannihatti Kumar, Rashmi Gangadharaiah
AUDITPLAN introduces a plan-then-answer method for safety alignment in language models, where the model first generates a compact structured safety plan before responding. The plan includes a threat label, intended action, and explicit constraints, allowing machine‑checkable auditing while remaining hidden from end users. Training combines supervised fine‑tuning with reinforcement learning using the FAITHGATE reward, which only rewards correct plans, thereby reducing unsafe shortcuts and improving robustness across Qwen model variants.
By Sai Sri Pushpa Jampani, Kshitij Mishra, Asif Ekbal
The paper investigates how to personalize a cross-user surface electromyography (sEMG) encoder when only a few calibration repetitions are available. Four methods—prototypical adaptation, linear probes, scaled fine‑tuning, and full fine‑tuning—were evaluated across 77 subjects on two databases. Full fine‑tuning consistently achieved the highest accuracy, but a gradient‑free prototypical rule captured 52–78 % of the benefit without per‑user weight copies, enabling quick donning‑time personalization.
By Jethro Odeyemi, W. J. Zhang
The paper introduces an AI-assisted pipeline for retrieving goldsmith marks from silverware images, combining mark localization with metric‑learning fine‑tuning on three backbone models (ResNet‑50, ViT‑S/16, and DINOv2 ViT‑S/14). Systematic tests of cropping strategies show that manual cropping and metric‑learning fine‑tuning yield the best performance, with DINOv2 ViT‑S/14 achieving 62.63% mAP and 73.74% Top‑1 accuracy. The authors release a manually annotated dataset, code, and a public web interface to support reproducibility and adoption in digital humanities.
By Atmik Tiwari, Vincent Christlein, Mark Fichtner, Freya Gohlke, Birgit Sch\"ubel, Theresa Witting, Heike Zech, Mathias Zinnen
The paper compares convolutional neural networks (CNN), Vision Transformers (ViT), and hierarchical Swin Transformers for quark‑gluon jet classification using a three‑channel jet‑image representation. CNN and Swin models outperform ViT, indicating that local jet substructure is crucial for discrimination. The study also shows that block‑wise fine‑tuning, Momentum Contrast pretraining, and a compact Swin variant can improve performance while reducing parameters.
By Daeun Kim, Jaeyoon Cho, Jiwon Lee, Wonjun Jeong, Hyeongwoo Noh, Giyeong Kim, Seunghwan Yang, MinJung Kweon
FedVideoMAE is a federated learning framework for short‑form video moderation that keeps raw videos on the device and uses a frozen VideoMAE backbone with lightweight LoRA and prompt parameters. Each training round performs self‑supervised masked video reconstruction while applying client‑side differential privacy and pairwise masked aggregation of adapter updates, keeping violence labels out of the federation. On the RWF‑2000 dataset, the method reduces the model‑state payload by 28.3× and achieves 77.25% accuracy without privacy mechanisms, dropping to 65.25–66.00% under differential privacy and secure aggregation.
By Ziyuan Tao, Chuanzhi Xu, Sandaru Jayawardana, Adnan Mahmood, Wei Bao, Kanchana Thilakarathna, Teng Joon Lim
The paper evaluates twelve financial sentiment models—including dictionary-based methods, finance-specific transformers, and open-source large language models—using linguistic and economic validity criteria. General-purpose LLMs match finance-specific transformers in classification performance but do not yield stronger economic relationships. While several models correlate with earnings surprises, none shows a significant link to next‑day stock returns, and performance is strongest for large earnings beats or misses.
By Arslan Bisharat, Oudom Hean
The paper investigates how Large Language Model (LLM) agents can collaborate on a shared task under information asymmetry, using a table‑top version of Einstein Puzzles. It introduces a fine‑tuning‑plus‑verifier framework that equips agents with communication strategies and environmental verification signals. Results show that aligned communication is crucial for rule understanding and human trust, while a verifier improves task comprehension and promotes safer, interpretable collaboration.
By Run Peng, Ziqiao Ma, Amy Pang, Sikai Li, Zhang Xi-Jia, Yingzhuo Yu, Cristian-Paul Bara, Joyce Chai
The paper introduces pre‑trained models for extracting variant‑phenotype relations from biomedical text, focusing on the SNPPhenA corpus. Fine‑tuning small BERT‑based models, especially DeBERTa, achieves performance close to the current state‑of‑the‑art. Moreover, careful fine‑tuning of Google’s Gemini Pro 1.0 surpasses existing benchmarks on both sentence‑level and abstract‑level relation extraction tasks.
By Claudiu Creanga, Liviu P. Dinu, Daniela Gifu
SlugTrails is a new egocentric benchmark for floor‑plan‑based indoor visual localization in large buildings, featuring 30 Hz Aria glasses recordings across three campus buildings and six floors. The dataset includes CAD‑derived floor plans with semantic classes, circulation masks, and laser‑surveyed anchors for trajectory alignment. Five representative systems were evaluated, showing that stock checkpoints perform poorly while fine‑tuning on SlugTrails significantly improves performance and cross‑dataset generalization, indicating that data scarcity limits current methods.
By Yunqian Cheng, Roberto Manduchi
UniPolicy is a multi-policy alignment framework for search advertising that jointly optimizes relevance, click propensity, and commercial value. It uses objective-specific prefix tokens, sparse MoE-LoRA routing, and residual FFNs to decouple parameters within a shared backbone, and builds pairwise preferences from multi-stage behavioral feedback to improve generation. In large-scale offline tests and a 7‑day online A/B test, UniPolicy achieved balanced gains across metrics, boosting CTR by 0.71%, RPS by 1.58%, and revenue by 1.32% while keeping latency stable.
The paper introduces DART, a training‑free technique that combines low‑rank coordinate transport with target‑schedule response calibration to improve the reuse of LoRA adapters in few‑step video diffusion models. By avoiding source training videos and using forward evaluations, DART raises the joint quality score on a four‑step Wan2.2 target from 0.9029 to 0.9227 and shifts macro functional retention from negative to positive. Component analysis shows that calibration drives most of the quality gains, while coordinate transport adds complementary benefits, and the method demonstrates consistent improvements across additional targets.
SlugTrails is a new egocentric benchmark for floor‑plan‑based indoor visual localization in large buildings, featuring 30 Hz Aria glasses recordings across three campus buildings and six floors (22 089 m²). The dataset includes CAD‑derived floor plans with semantic classes, circulation masks, and laser‑surveyed anchors, and supports three realistic sensing protocols: single walking frames, stationary multi‑view sweeps, and walking streams with odometry. Evaluation of five geometric and learned systems shows that stock models perform poorly, but fine‑tuning on SlugTrails significantly improves performance and cross‑dataset generalization, indicating that data scarcity limits current localization methods.
BadQubits is an LLM-based framework that statically analyzes OpenQASM 2.0 circuits before execution to detect structurally harmful patterns. The system evaluates four large language model architectures on 1,500 circuits, achieving 92.67% classification accuracy and 96.1% recall for harmful circuits with a fine‑tuned Qwen Coder 2.5 7B model. Comparative experiments show that LLMs retain sequential token structure, outperforming a bag‑of‑gates CNN, and that model decisions correlate with threat‑defining features such as SWAP density and measurement timing.
By Justin Woodring, Lamine Noureddine, Aisha Ali-Gombe
arXiv:2403.17612v3 Announce Type: replace
Abstract: Labeling corpora constitutes a bottleneck to create models for new tasks or domains. Large language models mitigate the issue with automatic corpus...
By Christopher Bagdon, Prathamesh Karmalker, Harsha Gurulingappa, Roman Klinger
The paper introduces Temperon, a training strategy that uses plain SGD for the first 43% of the epoch budget and then hands off to a SAM‑wrapped Muon refiner for the remaining training. On datasets such as CIFAR‑10/100, SVHN, and Tiny ImageNet, Temperon achieves the same or better accuracy as full‑time SAM while reaching key performance targets faster and at lower cost. Ablation studies show that the Muon refiner contributes the majority of the performance gain, while the initial SGD explorer and its restarts add negligible benefit.
By Stamatis Mastromichalakis