This paper proposes Supervised Memory Training (SMT), a method for training nonlinear RNNs that sidesteps recurrent credit propagation entirely.

This paper presents a study on improving healthcare-domain translation for four low-resource languages using Arabic and Persian as pivots, and introduces three transfer strategies.

CSULoRA is a post-hoc method that corrects trained LoRA adapters by estimating a safety-aligned subspace and solving a penalized minimum-change problem to attenuate unsafe update directions while pres…

The paper demonstrates that the phenomenon of 'subliminal learning,' where behavioral traits are transmitted between language models, is not a fundamental learning mechanism but rather a fragile artif…

The paper introduces NaRA, a noise-aware LoRA technique that dynamically adapts fine-tuning parameters based on the noise level during diffusion, significantly improving the performance of Diffusion L…

The paper investigates whether using fine-grained, tensorized adapters (CP components) instead of standard LoRA ranks improves the accuracy-budget trade-off in PEFT, finding that while they fill budge…

The paper quantifies the exact parametric memory capacity of LLMs using LoRA and proposes a new optimization strategy, MemFT, to enhance memory fidelity.

The paper introduces FoLoRA, a novel optimization framework that uses a generalized Rayleigh quotient to achieve a superior balance between adapting foundation models to specific tasks and preserving…

This paper proposes a domain-specialized large language model, PoetryQwen, for precise translation and emotional understanding of classical poetry.

TalTech submitted top-ranking systems to the Beyond Transcription Challenge using fine-tuned Voxtral models and reinforcement learning against Open Medical Concept F1.

LayerRoute introduces a lightweight, input-conditioned adapter that selectively skips transformer blocks in agentic language models, achieving significant FLOPs reduction while improving performance.

This paper investigates the effectiveness of incorporating synthetic speech data in Automatic Speech Recognition (ASR) Systems for three Indic languages by analyzing performance gains, script sources,…

The paper introduces Script-Normalized WER (SN-WER), a novel evaluation metric that transliterates ASR transcripts into a canonical script to accurately measure speech recognition performance across d…

This paper introduces a pipeline to extract grammatical rules, example sentences, and lexicons from grammar books and generates synthetic parallel corpora for fine-tuning machine translation models on…

This paper investigates the application of Parameter-Efficient Fine-Tuning (PEFT) methods, specifically adapters and LoRA, to large pretrained models for instance segmentation, demonstrating that thes…

This paper introduces a new R package for Non-negative Matrix Factorization (NMF) and compares its performance systematically with two other R packages using real-world data.

The paper proposes Locality-Aware Redundancy Pruning (LoRP), a training-free method that prunes LLM layers by exploiting localized inter-layer redundancy, leading to improved efficiency while maintain…