LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2610.08118v1 Announce Type: new Abstract: Covariate-aware time-series foundation models (TSFMs) promise training-free what-if answers for instrumented plants: the change in output that a differ...
arXiv:2610.07720v1 Announce Type: cross Abstract: Multi-reference image generation requires preserving the appearance of multiple subjects while composing them into a coherent scene. However, existin...
arXiv:2509.18169v4 Announce Type: replace Abstract: Tasks on complex systems require high-precision numerical computation to support decisions. However, current large language models (LLMs), even wit...
arXiv:2607.09042v2 Announce Type: replace Abstract: Reinforcement learning is increasingly used to fine-tune vision-language-action (VLA) models, but robot interaction is expensive and learning becom...
arXiv:2610.06505v2 Announce Type: replace Abstract: Proactive AI assistants continuously observe a user's activity and decide whether to provide new guidance or remain silent. They should provide app...
arXiv:2610.07186v1 Announce Type: new Abstract: Large language models make claims about themselves that are both consequential and increasingly difficult to verify from behavior alone. How can we dis...
arXiv:2610.07563v1 Announce Type: new Abstract: Large language models (LLMs) have the potential to meet a key goal in economics: a quantitative model of household decision making, across a variety of...
arXiv:2610.07774v1 Announce Type: new Abstract: Vision-language models (VLMs) face compositional safety risks where harmful intent emerges from the interaction between visual and textual inputs. As m...
arXiv:2610.08604v1 Announce Type: new Abstract: Automatic Speech Recognition (ASR) systems often show uneven performance across demographic groups, and errors can be especially difficult to address f...
The paper investigates how vision‑language models acquire and specialize semantic capabilities during fine‑tuning, proposing a trajectory‑based framework that separates acquisition, optima, and specialization phases. It introduces Structured Semantic Routing (SSR) to analyze how supervision representation affects what is learned, showing that SSR improves name‑free attribute‑profile retrieval and that different capabilities peak at different training stages. The study reveals that continued optimization can preserve target‑class retrieval while diminishing transferable semantic knowledge, highlighting a trade‑off between specialization and generalization.
The paper investigates how diffusion models, even after fine‑tuning to unlearn harmful concepts, still retain a linear residual of those concepts in token embeddings. It introduces SubAttack, a jailbreak method that extracts this residual by learning orthogonal attack tokens composed of interpretable textual elements, and SubDefense, a plug‑and‑play defense that projects out the same subspace to suppress the residual. Experiments show SubAttack outperforms prior attacks in power and transferability, while SubDefense offers stronger robustness and better preservation of safe generation quality.
arXiv:2610.06896v1 Announce Type: new Abstract: Frontier multimodal large language models (MLLMs) are increasingly positioned as general purpose visual reasoners as part of the quest for artificial g...
arXiv:2610.07711v1 Announce Type: new Abstract: Accurate nuclei instance segmentation is essential for quantitative renal pathology, yet general-purpose models often struggle with low contrast, dense...
arXiv:2610.08109v1 Announce Type: new Abstract: Cardiac magnetic resonance imaging reconstruction aims to recover high-quality images from undersampled acquisitions, enabling faster scans while prese...
arXiv:2604.09045v2 Announce Type: replace Abstract: Recent works on 3D scene understanding leverage 2D masks from visual foundation models (VFMs) to supervise radiance fields, enabling instance-level...
The paper investigates how a small grounding model for a GUI agent should receive the action type. Using Qwen2‑VL‑2B fine‑tuned with LoRA on Android, the authors compare a flat baseline with five conditioning methods—auxiliary loss, hard‑routed action word, additive learned embedding, prepended learned token, and prompt word—under matched data, compute, and decoding settings. Results show that auxiliary loss, additive embedding, and prompt word each improve hit@0.10 by five to seven points over the baseline, while hard routing and prepended token perform similarly to the baseline; however, removing a problematic off‑screen touch point class lifts the baseline by nearly seven points, after which no method outperforms it. "whyItMatters":"The study identifies effective strategies for encoding action type in small grounding models, which could improve the accuracy of GUI agents in real‑world Android applications."
Fiorillo v0.5 is an open 4‑billion‑parameter model that reads a randomized trial article (cut to 6,144 tokens) and predicts whether an intervention significantly increased, decreased, or had no significant effect on an outcome. Fine‑tuned on 1,431 license‑clean training articles, it achieved an expected calibration error of 0.0168, log loss 0.8603 lower than the prior, and macro‑F1 of 0.9248 on a public test split of 1,218 prompts. The model’s release, licensed under Apache 2.0, met all four pre‑registered criteria on the Open Science Framework and was validated against the evaluated predictions.
The paper introduces SAGA, a framework that enables large language model agents to evolve by abstracting experiences into reusable principles, procedures, and episodic descriptions. SAGA transforms interaction trajectories into hierarchical knowledge with explicit applicability conditions, linking them back to execution evidence. Experiments on ScienceWorld and ALFWorld show that this execution–abstraction feedback loop improves task performance, and ablation studies confirm the importance of contextual instantiation and action regulation.
JIVEAdapter is a multi-task additive low-rank adapter that decomposes weight updates into a shared Joint component and a per-task Individual component, inspired by Joint and Individual Variation Explained (JIVE). It penalizes Individual structures to remain near-orthogonal to the Joint, ensuring interpretable separation of shared and task-specific signals, and allocates rank adaptively between shared and individual pools. The Joint component is learned once and frozen, then reused as a prior for new tasks, achieving competitive performance on GLUE and SuperGLUE with DeBERTaV3-base without additional modules.
The paper introduces AMBER, an append‑only memory framework for language‑model agents that interact over long horizons. AMBER lets agents jointly learn to reason, act, and write free‑form memory, guaranteeing retention by construction and enabling end‑to‑end reinforcement learning without extensive curated data. Experiments on WebArena Lite show AMBER outperforms overwrite‑based memory by 4.09 percentage points in average success and improves task completion rates in repeated runs.