LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2609.16229v1 Announce Type: new Abstract: Machine unlearning aims to remove specific knowledge from a trained large language model (LLM) without retraining from scratch. Existing methods modify...
arXiv:2508.15774v2 Announce Type: replace Abstract: Visual diffusion models achieve remarkable progress, yet they are typically trained at limited resolutions due to the lack of high-resolution data...
arXiv:2609.16204v1 Announce Type: new Abstract: Safety guardrails in open-weight language models can be readily bypassed using Refusal Feature Ablation (RFA), a technique that identifies and projects...
The paper introduces DiaWhisper-DPO, an end‑to‑end model that fine‑tunes Whisper-large-v3 with LoRA and a frame‑level role head to transcribe and attribute utterances in clinical interviews. It further refines the system using failure‑mined preference optimization (DPO) that leverages genuine decoding failures as rejected completions, eliminating the need for human preference data. On the DAIC‑WOZ dataset, DiaWhisper‑DPO attains 0.973 role accuracy and 0.119 DER, outperforming cascaded baselines by 72% and dramatically reducing seed variation, while also improving performance on the cross‑lingual PDCH‑HAMD dataset.
The paper introduces EBL, an Efficient Broad Learning framework designed for distributed adaptive harmonic estimation in power grids affected by electric vehicle charging. It leverages a quantised FPGA implementation to provide high‑accuracy, half‑cycle input harmonic predictions with ultra‑low latency, outperforming existing FPGA methods by 17.4×. The online transfer learning component enables rapid adaptation across multiple charging scenarios, while bespoke quantisation and sparsity reduce resource usage to just 5.9% of the LUTs on a Zynq Ultrascale+ FPGA, compared to 82% of the state‑of‑the‑art accelerator.
arXiv:2607.05364v4 Announce Type: replace-cross Abstract: Modern autoregressive ASR systems can emit timestamps as decoded tokens, enabling timestamped transcription without frame-level aligners or i...
arXiv:2601.18493v2 Announce Type: replace Abstract: Vision--language models (VLMs) show promise for disaster-response remote sensing, but existing benchmarks mainly emphasize scene-level or damage-ce...
The paper introduces VPRef, the first cross‑domain benchmark for Referring Remote Sensing Image Segmentation, containing 46,972 language‑image‑annotation triplets with a three‑tier linguistic hierarchy. It proposes a parameter‑efficient adaptation method based on the Segment Anything Model and Low‑Rank Adaptation, using pseudo‑label self‑training for visual drift and random multi‑granularity prompt mixing for textual drift. Experiments show the approach improves cross‑domain segmentation while altering only 1.08 % of the base model’s parameters, offering a strong baseline for future research.
arXiv:2609.16775v1 Announce Type: new Abstract: Annotating large radiology datasets is bottlenecked by the manual effort of delineating structures slice-by-slice in 3D volumes. Interactive methods re...
arXiv:2609.16909v1 Announce Type: new Abstract: With the increasing deployment of deep neural networks in critical systems, such as medical diagnostics and autonomous vehicles, ensuring their interpr...
arXiv:2609.17180v1 Announce Type: new Abstract: Multimodal counselor response generation (MCRG) aims to generate an appropriate counselor response from multimodal dialogue histories. Progress is limi...
arXiv:2609.16247v1 Announce Type: new Abstract: Large language models sometimes behave in ways resembling human emotional responses, and recent work has identified internal representations that may e...
arXiv:2602.10480v4 Announce Type: replace Abstract: Large language models (LLMs) exhibit strong general-purpose reasoning capabilities, yet they frequently hallucinate when used as world models (WMs)...
GrowMTP is a method that trains a draft head entirely within the reinforcement learning (RL) loop, using supervision from the RL verification step and a rollout distribution that is narrower than pretraining. By detaching draft‑head updates from the policy backbone, it enables online training of the draft head from scratch. Experiments on Qwen3‑4B, MiMo‑7B‑SFT, and Qwen3.5‑4B‑Base show rollout speedups ranging from 1.36× to 2.13× and overall end‑to‑end speedups from 1.20× to 1.60×, making it a modular acceleration component for RL frameworks lacking pretrained draft heads.
arXiv:2507.21931v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) often produce plausible but poorly-calibrated answers, limiting their reliability on reasoning-intensive tasks....
arXiv:2607.27245v2 Announce Type: replace-cross Abstract: Modern policing faces a "visibility paradox" where law enforcement agencies possess petabytes of Body-Worn Camera (BWC) footage that remains...
arXiv:2609.16059v1 Announce Type: cross Abstract: Multimodal instruction following (MMIF) is crucial for building generalist agents. However, current training paradigms rely heavily on Supervised Fin...
arXiv:2609.17458v1 Announce Type: cross Abstract: Table understanding is a core task in document intelligence, encompassing two key subtasks: table reconstruction and table visual question answering...
arXiv:2609.16997v1 Announce Type: new Abstract: Crisis sentiment analysis is especially challenging for low-resource languages such as Bangla, where language, context, and public reaction shift rapid...
The paper presents the first systematic evaluation of out‑of‑distribution generalization for congenital heart disease (CHD) segmentation, using the ImageCHD cohort as a held‑out target. It compares several segmentation architectures under different training regimes, showing that in‑distribution performance is a poor predictor of cross‑cohort robustness: nnU‑Net drops from 0.77 to 0.51 Dice, while SwinUNETR maintains higher performance at 0.67 Dice. Limited target‑domain adaptation with only 11 labeled ImageCHD cases boosts all SwinUNETR variants above 0.76 Dice, highlighting the importance of explicit cross‑dataset testing.