LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2610.09772v1 Announce Type: new Abstract: Small language-model agents on edge devices must hold a persona and reason correctly at once, inside one context window that fills with conversational...
arXiv:2610.09835v1 Announce Type: new Abstract: Continual pre-training and fine-tuning in Large Language Models (LLMs) inevitably induce catastrophic forgetting, typically mitigated by replay using o...
arXiv:2610.09788v1 Announce Type: new Abstract: Reward modeling often requires jointly representing and reasoning over multiple evaluation criteria, yet verbalizing this process token by token can in...
arXiv:2610.09486v1 Announce Type: cross Abstract: Spoken language identification (LID) aims to recognize the target language regardless of accent. In practice, however, LID models fine-tuned from sel...
arXiv:2606.22272v2 Announce Type: replace Abstract: Applying pre-trained language models to new domains through full fine-tuning is computationally expensive and prone to catastrophic forgetting. To...
arXiv:2605.09492v3 Announce Type: replace Abstract: Reliable text generation is critical for deploying large language models (LLMs) in real-world applications, particularly in high-stakes domains suc...
arXiv:2609.35821v2 Announce Type: replace Abstract: Disaster social sensing converts public social-media posts into evidence for situational awareness and humanitarian response, but plausible LLM-gen...
arXiv:2610.09450v1 Announce Type: new Abstract: Pixel-space diffusion models avoid the lossy VAE of latent models, which suggests an advantage on downstream tasks where fine-grained detail matters. W...
arXiv:2610.10163v1 Announce Type: new Abstract: Linking people's appearance and actions to character identities is essential for understanding video narratives. We present a framework for identity-aw...
arXiv:2604.19710v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models bring rich world knowledge and reasoning capabilities to autonomous driving. However, most driving VLAs are tra...
arXiv:2610.10388v1 Announce Type: cross Abstract: Recent advances in multimodal foundation models have made them capable generalist physical agents for a range of manipulation tasks. However, success...
CM-DPO introduces a Constraint-Margin Direct Preference Optimization method that replaces the binary preference signal of traditional DPO with a continuous margin based on a deterministic symbolic verifier, scaled by violation severity. Hard and soft constraints are separated via a lexicographic objective to prevent hard constraints from being traded off against preferences. Using procedurally generated constraint profiles and minimal-edit distillation within the SynPlan-R framework, an 8B model fine‑tuned with CM‑DPO achieves high pass and solve rates on several planning benchmarks, matching multi‑agent systems with lower latency and outperforming GPT‑4o on unseen tasks.
The study investigates how to adapt automatic speech recognition (ASR) models to child speech while preserving adult performance, focusing on Arabic and English data. It compares full fine‑tuning, LoRA, and post‑hoc weight‑space merging across encoder–decoder, encoder–CTC, and AudioLLM‑based ASR systems, using child and adult benchmarks. Results indicate that child adaptation is essential, especially for non‑native speakers, but direct adaptation can degrade adult accuracy; bilingual adaptation and weight‑space merging techniques help balance the trade‑off, with encoder–decoder fine‑tuning still yielding the best raw WER for bilingual models.
arXiv:2610.09737v1 Announce Type: cross Abstract: When does distribution alignment help a frozen foundation-model embedding generalize across acoustic domains? For cross-domain mosquito-species class...
arXiv:2610.08826v1 Announce Type: new Abstract: Full-sphere panoramic cameras let fixed monitoring systems and mobile robots track people in every direction, but a planar bounding box does not fully...
arXiv:2610.10335v1 Announce Type: new Abstract: Visual in-context learning (ICL), well suited to label-scarce medical imaging, uses support image-label pairs to demonstrate input-output mappings, whi...
arXiv:2609.31765v2 Announce Type: replace Abstract: Accurate and rapid prediction of the aerodynamic drag coefficient ($C_D$) is essential for vehicle design, particularly during early-stage design,...
The paper introduces DIGHT, a co‑adaptive framework that couples a Digital Human Interaction Generator with a Humanoid Tracking policy. DIGHT first runs multiple text‑conditioned interaction candidates in simulation, then builds physics‑grounded preferences from the rollouts—covering executability and interaction fidelity—and uses diffusion‑based direct preference optimization to align the generator without back‑propagating through the simulator. The aligned generator supplies reference motions for fine‑tuning the tracker, leading to more physically plausible and faithful humanoid interactions in simulation.
arXiv:2610.09226v1 Announce Type: cross Abstract: Data collection using Unmanned Aerial Vehicles (UAVs) is challenging when LoRa IoT Devices (IoTDs) duty-cycle to conserve battery. Under energy const...
arXiv:2610.04238v2 Announce Type: replace-cross Abstract: Humanoid robots could transport payloads substantially heavier than themselves by pulling passive wheeled vehicles instead of carrying the lo...