LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2605.18904v2 Announce Type: replace-cross Abstract: Model merging consolidates independently fine-tuned checkpoints without joint training or access to task data. Dynamic methods retain task-sp...
The paper introduces LSA-PAST, a parameter‑efficient approach for compositional incremental learning that addresses the challenge of learning new state‑object compositions while preserving knowledge of previously seen compositions. It combines Layer‑Specific Adaptation using Low‑Rank Adaptation (LoRA) with depth‑specialized adapters for states, objects, and compositions, and employs Prototype‑Anchored Adapter‑Space Transport (PAST) to map past prototypes into the current adapter space without rehearsal. Experiments show that LSA-PAST achieves state‑of‑the‑art accuracy‑forgetting trade‑off performance in this setting.
arXiv:2610.27904v1 Announce Type: new Abstract: Staged post-training of multimodal foundation models chains vision-language alignment, reasoning distillation, and domain tuning, yet how each phase tr...
arXiv:2610.27785v1 Announce Type: cross Abstract: Speech separation (SS) has witnessed substantial progress in recent years with the advent of neural network-based methods, achieving notable improvem...
The study evaluates how well time‑series foundation models (TSFMs) can be adapted for electrical load forecasting. It compares pretrained inference, full fine‑tuning, and low‑rank adaptation (LoRA) across four load aggregation levels, using MOIRAI 1.0 Large as the main backbone and Chronos‑2 as a secondary model. LoRA achieves a 7.5% average NMAE reduction on MOIRAI while updating only about 1% of the parameters, offering a strong accuracy‑efficiency trade‑off, though benefits vary in out‑of‑distribution scenarios.
arXiv:2610.28411v1 Announce Type: cross Abstract: Deep learning models have become essential tools in medical imaging, yet training them end-to-end for diverse tasks remains challenging due to limite...
The paper investigates whether compact AI agents can display strategic behavior in poker under hidden information and whether preference optimization can surpass static and zero‑shot policies. After evaluating a static baseline and three frozen language models (SmallThinker, Qwen3, Gemma‑3), the authors introduce Strategic Preference Optimization with KL‑anchored Equilibrium (SPOKE), which blends teacher‑relative value penalties, policy anchoring, risk constraints, and structured rationale supervision. SPOKE outperforms other methods on Kuhn and Leduc games, achieving the lowest mean exploitability and the highest six‑max top‑1 agreement while maintaining teacher‑consistent behavior.
arXiv:2610.27645v1 Announce Type: new Abstract: As computer-use agents (CUAs) move to long-horizon workflows spanning multiple applications, undetected errors can silently corrupt persistent state an...
arXiv:2610.27670v1 Announce Type: new Abstract: This paper introduces a novel framework for efficiently evaluating in-game sound designs using multimodal learning and reinforcement learning. Sound de...
arXiv:2610.27847v1 Announce Type: new Abstract: Scaling the training of Large Language Model (LLM) agents typically requires a large collection of executable environments, whose construction, mainten...
arXiv:2610.28361v1 Announce Type: new Abstract: Long-horizon deep search requires LLM agents to iteratively decompose complex information needs, gather evidence from external sources, and maintain a...
arXiv:2610.28537v1 Announce Type: new Abstract: Post-training quantization (PTQ) compresses the weights of a trained model with limited compute and data. Down to 4 bits it is near-lossless, but at 2...
arXiv:2610.26891v1 Announce Type: cross Abstract: Sparse routing reduces per-token computation but leaves the full expert bank resident in memory. We study expert pruning for speech-centric omni-moda...
arXiv:2610.26963v1 Announce Type: cross Abstract: Discovering governing partial differential equations (PDEs) from observed data is a central inverse problem in computational science and engineering:...
arXiv:2610.27942v1 Announce Type: cross Abstract: Automated respiratory sound classification enables continuous, non-invasive respiratory assessment, yet long-term deployment remains challenging due...
arXiv:2610.28337v1 Announce Type: cross Abstract: Emoji are widely treated as compact affective tokens whose meaning is summarised by a single sentiment score. We argue that this picture is incomplet...
arXiv:2610.28364v1 Announce Type: cross Abstract: Local Retrieval-Augmented Generation (RAG) systems are vulnerable to indirect prompt injection and retrieval poisoning, where malicious instructions...
arXiv:2610.28434v1 Announce Type: cross Abstract: Large language models leave model-specific traces in their generated text, but it remains unclear how finely these fingerprints can distinguish relat...
arXiv:2610.28586v1 Announce Type: cross Abstract: Agentic on-policy distillation (OPD) trains a student agent on its own trajectories while a teacher scores every token. A natural explanation of wher...
arXiv:2510.14697v2 Announce Type: replace Abstract: Model merging aims to integrate task-specific abilities from individually fine-tuned models into a single model without extra training. In recent m...