LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2610.07722v1 Announce Type: new Abstract: Activation steering provides a lightweight and flexible way to control large language model (LLM) behavior. However, effective steering requires more t...
arXiv:2610.08063v1 Announce Type: cross Abstract: This paper presents the HINTT system submitted to the 2nd Challenge and Workshop on Multilingual Conversational Speech Language Model (MLC-SLM). We a...
arXiv:2603.08231v2 Announce Type: replace-cross Abstract: Paralinguistic speech tasks are often considered relatively language-agnostic, as they rely on extralinguistic acoustic cues rather than lexi...
arXiv:2610.07326v1 Announce Type: new Abstract: Universal object localization in X-ray security inspection is critical for automated threat detection in safety-critical venues. However, unlike everyd...
arXiv:2610.08315v1 Announce Type: new Abstract: Counter-UAV systems based on thermal infrared detection must stay accurate as operational datasets evolve, yet sequential fine-tuning causes catastroph...
arXiv:2610.08620v1 Announce Type: new Abstract: High-beam-count LiDAR sensors are costly, yet many perception pipelines require dense angular sampling. Using a pretrained Stable Diffusion model as th...
arXiv:2610.08133v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models achieve strong robotic manipulation performance but incur high computational costs from processing long token seq...
arXiv:2606.10142v2 Announce Type: replace Abstract: Recent advances in 3D generation have led to substantial improvements in realism, controllability, and efficiency, yet the evaluation of 3D assets...
The paper investigates how small language models acquire abstract reasoning skills on the ARC‑TGI benchmark, which groups grid‑transformation tasks into controllable families and allows resampling, spatial shifts, and cross‑benchmark transfer. Over 1,000 supervised fine‑tuning runs across decoder‑only, encoder‑decoder, and mixture‑of‑experts families, the study finds that high in‑distribution accuracy is possible but depends heavily on optimization and is uneven across task families. Performance drops sharply outside the training distribution, and gains from larger training sets or additional in‑context examples vary by model family; attention diagnostics reveal distinct patterns but do not explain causal mechanisms.
The paper presents a Vision Transformer-based model for subseasonal soil‑moisture forecasting over Europe, showing that forecast skill depends heavily on how the prediction problem is formulated. By using residual learning and forecasting root‑zone soil moisture in physical units, the model outperforms persistence and existing deep‑learning and ECMWF baselines, providing well‑calibrated probabilistic predictions. However, predicting flash drought onset—defined by rapid multi‑pentad intensification—remains a challenge shared by all current subseasonal‑to‑seasonal systems.
The paper critiques the use of pass@$k$ as a sole metric for evaluating reinforcement‑learning post‑training on language models, showing that it ignores diversity in model outputs. Experiments on Qwen2.5‑1.5B‑Instruct trained with Group Relative Policy Optimization (GRPO) and rejection‑sampling fine‑tuning (RFT) reveal that these methods shift token‑level, answer‑level, and unique‑answer diversity in opposite directions, yet pass@$k$ fails to capture these differences. Even when restricting to verifier‑correct completions, diversity gaps persist, and pass@$k$ does not consistently identify the better performing arm on hard problem subsets, indicating that the metric can mask true capability changes.
The paper introduces Mask Fine‑Tuning (MFT), a new approach for adapting Vision‑Language Models that avoids modifying backbone weights. MFT learns masks to selectively route information through existing pretrained connections, dynamically uncovering subnetworks that better align with downstream tasks. Experiments demonstrate that MFT consistently outperforms both Full Fine‑Tuning and Parameter‑Efficient Fine‑Tuning across multiple benchmarks, while also offering insights into how pretrained VLMs reorganize their internal pathways during adaptation.
The paper introduces EmoNet‑Face‑HQ, a fine‑grained emotion recognition benchmark that uses generated portraits and a 40‑category taxonomy to evaluate vision‑language models (VLMs). It finds that VLMs perform poorly when asked to generate responses but can match or surpass a fine‑tuned model (Empathic‑Insight‑Face) when their logits are read directly as binary queries. The study shows that the benchmark’s difficulty lies in the readout process rather than in perception, and that graded probability outputs yield better performance than simple yes/no questions.
The paper introduces a new benchmark dataset of over 6,000 high‑resolution images for detecting and segmenting Western bluebirds in natural, cluttered scenes. Experiments show that supervised detectors such as Faster R‑CNN and RT‑DETR outperform open‑vocabulary models in zero‑shot settings, though fine‑tuned YOLO‑World can compete. Segmentation results favor Mask R‑CNN for mask quality, while YOLOv8‑Seg offers the best precision and speed. The study also identifies multiple factors—scale, brightness, contrast, clutter, blur, crowding, and session variation—as contributors to detection failures.
The study introduces a multitask conditional generative adversarial network (MT‑cGAN) that simultaneously synthesizes high‑resolution DESS‑like images and segments knee cartilage and menisci directly from quantitative MRI echo images. Evaluated on 508 knee MRIs from 361 subjects, MT‑cGAN achieved a mean Dice score of 0.84 for segmentation and the lowest coefficient of variation for T1ρ (1.84%) and T2 (1.81%) quantification, outperforming existing conditional GAN approaches. By eliminating the need for separate high‑resolution morphological scans, the method shortens scan times and supports clinical adoption of quantitative MRI.
arXiv:2610.07229v1 Announce Type: new Abstract: Motivated by sequence-to-sequence transport in the context time-series domain adaptation, we study the problem of transportation between trajectories o...
arXiv:2610.07848v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning (PEFT) has become a standard approach for adapting large language models to downstream tasks. However, most existing...
arXiv:2609.33155v2 Announce Type: replace Abstract: Test-time scaling and post-training have improved LLM performance in coding and mathematical reasoning, but their effectiveness for individual stan...
arXiv:2604.18226v2 Announce Type: replace Abstract: Automated analysis of customer feedback on social media is hindered by three challenges: the high cost of annotated training data, the scarcity of...
arXiv:2610.07484v1 Announce Type: new Abstract: Self-supervised EEG models often reconstruct masked waveforms or predict discrete codes. We study a task-aligned alternative: masked band-power predict...