#pretrained-models News & Analysis

6 articles tagged with #pretrained-models. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

6 articles

AIBullisharXiv – CS AI · Jun 17/10

🧠

MindVoice: Reconstructing Intelligible Speech from Non-invasive Neural Signals with Pretrained Priors

Researchers introduce MindVoice, a neural decoding framework that reconstructs intelligible speech from non-invasive brain recordings (EEG/MEG) by leveraging pretrained AI models to compensate for signal degradation. The method separates semantic content recovery from acoustic attribute estimation, then fuses these with generative speech models to produce natural utterances, significantly outperforming existing approaches and advancing brain-computer interface technology.

AIBullisharXiv – CS AI · May 277/10

🧠

Trust Region Q Adjoint Matching

Researchers introduce Trust Region Q-Adjoint Matching (TRQAM), a reinforcement learning algorithm that stabilizes off-policy fine-tuning of pretrained flow policies by adaptively controlling deviation through trust-region constraints. The method demonstrates significant performance improvements, achieving 68% success rate on offline RL tasks compared to 46% for previous approaches.

AIBullisharXiv – CS AI · Apr 137/10

🧠

Evidential Transformation Network: Turning Pretrained Models into Evidential Models for Post-hoc Uncertainty Estimation

Researchers propose Evidential Transformation Network (ETN), a lightweight post-hoc module that converts pretrained models into evidential models for uncertainty estimation without retraining. ETN operates in logit space using sample-dependent affine transformations and Dirichlet distributions, demonstrating improved uncertainty quantification across vision and language benchmarks with minimal computational overhead.

AINeutralarXiv – CS AI · Mar 37/105

🧠

Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Epsilon-Scheduling

Researchers identified that fine-tuning non-robust pretrained AI models with robust objectives can lead to poor performance, termed 'suboptimal transfer.' They propose Epsilon-Scheduling, a novel training technique that adjusts perturbation strength during training to improve both task adaptation and adversarial robustness.

AINeutralarXiv – CS AI · May 96/10

🧠

Channel-Level Semantic Perturbations: Unlearnable Examples for Diverse Training Paradigms

Researchers have developed a new technique called Shallow Semantic Camouflage (SSC) to protect personal data from unauthorized use in AI model training. The work addresses a critical gap where existing data protection methods fail under modern pretraining-finetuning paradigms, demonstrating that frozen pretrained weights significantly weaken previous unlearnable example approaches.

AIBullisharXiv – CS AI · Mar 36/102

🧠

Inner Loop Inference for Pretrained Transformers: Unlocking Latent Capabilities Without Training

Researchers propose a new inference technique called "inner loop inference" that improves pretrained transformer models' performance by repeatedly applying selected layers during inference without additional training. The method yields consistent but modest accuracy improvements across benchmarks by allowing more refinement of internal representations.