Home Knowledge Base Balanced Softmax

Balanced Softmax

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

AutoTail-BSFGM: Class-Balance-Aware Fine-Tuning for Chinese Scholarly Text Classification

arXiv:2606.03576v1 Announce Type: new Abstract: Scholarly text classification supports literature organization, subject indexing, and research intelligence, but Chinese scholarly corpora often contain imbalanced and semantically adjacent disciplinary labels. We propose AutoTail-BSFGM, a class-balance-aware fine-tuning method that combines an automatically gated tail-prior adjustment, a weak Balanced Softmax auxiliary loss, and Fast Gradient Method adversarial regularization. The method...

arXiv CS 7d ago

AutoTail-BSFGM: Class-Balance-Aware Fine-Tuning for Chinese Scholarly Text Classification

arXiv:2606.03576v2 Announce Type: replace Abstract: Scholarly text classification supports literature organization, subject indexing, and research intelligence, but Chinese scholarly corpora often contain imbalanced and semantically adjacent disciplinary labels. We propose AutoTail-BSFGM, a class-balance-aware fine-tuning method that combines an automatically gated tail-prior adjustment, a weak Balanced Softmax auxiliary loss, and Fast Gradient Method adversarial regularization. The method...

arXiv CS 1d ago

MS-DKC: A Dataset Knowledge Card Framework for Designing and Adapting Medical Image Segmentation Models

arXiv:2606.06103v1 Announce Type: new Abstract: Medical image segmentation is often framed as a search for stronger architectures, but this can obscure a more fundamental question: what does the dataset require from the model? In medical imaging, this requirement is shaped by foreground occupancy, morphology, boundary ambiguity, topology sensitivity, annotation quality, acquisition variation, and operating point. This paper introduces the Medical Segmentation Dataset Knowledge Card (MS-DKC),...

arXiv CS 5d ago

When Model Merging Breaks Routing: Training-Free Calibration for MoE

Announce Type: new Abstract: Model merging has emerged as a cost-effective approach for consolidating the capabilities of multiple LLMs without retraining. However, existing merging techniques, largely based on linear parameter arithmetic or optimization, struggle when applied to Mixture-of-Experts (MoE) architectures. We identify a critical failure mode in MoE merging, termed routing breakdown, in which the merged router fails to dispatch tokens to suitable experts.

arXiv CS 7d ago

Where does Absolute Position come from in decoder-only Transformers?

arXiv:2606.06160v1 Announce Type: new Abstract: RoPE-trained transformers distinguish absolute position in their attention patterns, even though RoPE encodes only relative offsets in the inner product. We trace this leakage to two architectural components, The causal mask is responsible for the first: its per-query softmax denominator depends on the absolute query position by construction. The residual stream supplies the second.

arXiv CS 5d ago

Magenta RealTime 2: Open and Local Live Music Models

We’re excited to share Magenta RealTime 2 (MRT2), a state-of-the-art open model and efficient real-time inference engine that enables you to build and play AI musical instruments on your laptop! To get started, download the apps on your MacBook (requires Apple Silicon). Unlike other large generative music models that work offline to turn a prompt into a track, MRT2 is a live, interactive model that you can control with MIDI and audio, in addition to text.

Hacker News 5d ago