LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2609.27227v1 Announce Type: new Abstract: Objective assessment of robotic surgery uses instrument kinematics, which must be reconstructed when only video is available. We introduce a kinematic...
arXiv:2609.28312v1 Announce Type: cross Abstract: We present VGM-VS, a visual servoing method built on a pretrained feed-forward visual geometry model. Given the current view and a reference image ca...
Adolescent Idiopathic Scoliosis is defined as a lateral curvature of the spine that develops during adolescence, without known cause. The condition can result in significant pain and disability, and o...
Removing an object from a real image requires more than synthesizing plausible content within a mask: the method must suppress residual object features, preserve the unedited scene, and generate repla...
We present VGM-VS, a visual servoing method built on a pretrained feed-forward visual geometry model. Given the current view and a reference image captured at the target configuration, we estimate the...
Robotic assembly in high-mixture settings requires adaptable systems that can handle diverse parts, yet current approaches typically rely on policies specialized to each insertion task. Although this...
Digital zoom transitions between dual cameras often exhibit conspicuous discontinuities in geometric structure and chromatic consistency, degrading the user experience. While recent dual-camera smooth...
Methods operating on Vision Transformer (ViT) feature spaces typically rely on Euclidean distance or cosine similarity. This assumes that every direction is equally meaningful, but there is no reason...
In-Context Learning (ICL) has become a cornerstone of modern LLM deployment. However, existing ICL post-training methods have a critical blind spot: they excel at extracting patterns from demonstratio...
The paper introduces a new evaluation protocol for diffusion data‑point unlearning that tracks whether each target is forgotten, remains forgotten, or reappears during subsequent deletions. It identifies a failure mode called sequential reappearance, where an instance that was initially forgotten later returns to the memorized regime without re‑use of the deleted data or adversarial fine‑tuning. The study also finds that reappearing targets exhibit a sharper local denoising‑loss geometry after deletion than those that remain forgotten.
arXiv:2609.26347v1 Announce Type: cross Abstract: The scarcity of non-English language data in specialized domains significantly limits the development of effective Natural Language Processing (NLP)...
arXiv:2609.26780v1 Announce Type: cross Abstract: Long-term conversational memory in multi-party settings requires more than retrieving relevant content from long-term conversations: it must distingu...
Pinocchio is an external calibrator that provides fast uncertainty estimates for black-box language models. It predicts the correctness of responses from seven trained LLMs with an AUROC of 0.862 and can transfer zero‑shot to thirteen unseen models from eight organizations. The method requires only a single forward pass and no access to the target model’s internal states, and a lightweight 0.8B checkpoint achieves comparable performance.
ToolCUA is an end‑to‑end agent that learns to optimally orchestrate GUI actions and tool calls for Computer Use Agents. It introduces a staged training pipeline that first scales interleaved GUI‑tool trajectories from static GUI data, then bootstraps decision making with single‑turn reinforcement learning, and finally refines performance via online agentic RL guided by a tool‑efficient path reward. On the OSWorld‑MCP benchmark, ToolCUA achieves 46.85% accuracy, a 66% relative improvement over the baseline and a 3.9% gain over GUI‑only models, setting a new state of the art for comparable‑scale models.
The paper investigates how the upper spectral tails of weight matrices in decoder‑only transformer language models influence reasoning behavior. By performing controlled interventions on the query–key product and comparing them to factor‑level surgeries, the authors find that edits targeting the spectral tail more strongly affect model performance across multiple checkpoints and reasoning benchmarks. The study also explores how inverse participation ratios predict accuracy transitions and shows that tail‑aware low‑rank adaptations converge faster than standard methods.
The paper audits the widely used ISOT/Kaggle Fake and Real News corpus and finds that extremely high reported accuracies (≈0.98) are largely due to shortcut signals rather than genuine veracity detection. A simple TF‑IDF linear classifier achieves perfect F1 when using only subject metadata, and even after removing metadata, newswire tags, and duplicate documents, the F1 drops only modestly, indicating that editorial style rather than specific tokens drives performance. Under topic‑disjoint and temporal transfer tests, performance collapses, and models transfer poorly to the independent LIAR benchmark, showing that within‑corpus scores reflect source and topic separability, not truth verification. whyItMatters:"The study demonstrates that current high accuracy metrics on this fake‑news dataset are misleading, highlighting the need for more robust evaluation protocols that guard against shortcut learning."
The paper investigates how different 4‑bit quantization techniques affect privacy when fine‑tuned small language models are deployed. It finds that methods using a calibration corpus, such as Activation‑aware Weight Quantization (AWQ) and Gradient‑based Post‑Training Quantization (GPTQ), prevent the reproduction of planted private records, whereas a calibration‑free format (GGUF Q4_K_M) leaks 5.3% of them. Across models ranging from 0.5 to 7 billion parameters, AWQ consistently leaks the least while maintaining minimal accuracy loss, indicating that the choice of 4‑bit method is a privacy decision as well as a performance one.
The study evaluates binary sex estimation from footwear outsole impressions using convolutional neural network (CNN) transfer learning compared to traditional feature-based classification. Fine‑tuned CNNs outperform classifiers that rely solely on handcrafted, geometric, and metadata descriptors, while frozen‑feature approaches provide a less computationally intensive alternative. Exploratory analysis links low‑dimensional CNN representations to measurable image properties such as frequency threshold ratio, contrast, and wavelet summaries, indicating that CNNs capture additional discriminative information.
Matryoshka Attribution (MAttr) is a mask‑learning method that identifies nested subsets of a language model’s internal components by minimizing downstream loss. It uses a differentiable sigmoid top‑k operator and randomizes sparsity during training to produce an attribution ordering of components. MAttr tops the Mechanistic Interpretability Benchmark leaderboard and can be applied via reinforcement learning to pinpoint weight changes that control behaviors such as refusal in Llama 3.1 8B Instruct, where restoring just 1% of weights removes refusals while preserving capabilities.
The study presents a daily runoff prediction model for the Ajichay River in northwest Iran, employing an ensemble of five Long Short-Term Memory (LSTM) units trained on varying time intervals (2–6 days). Each LSTM is fine‑tuned with Particle Swarm Optimization to enhance accuracy, and the ensemble’s performance on 2017–2018 data shows $R^2$ values between 74.95% and 91.42%, with RMSE and MSE also reported. Feature‑importance analyses identify key variables influencing runoff variations.