ニュース
Breaking PEFT Limitations: Leveraging Weak-to-Strong Knowledge Transfer for Backdoor Attacks in LLMs
arXiv:2409.17946v4 Announce Type: replace-cross Abstract: Despite being widely applied due to their exceptional capabilities, Large...
Breaking Language Barriers or Reinforcing Bias? A Study of Gender and Racial Disparities in Multilingual Contrastive Vision Language Models
arXiv:2505.14160v4 Announce Type: replace Abstract: Multilingual vision-language models (VLMs) promise universal image-text retrieval, yet their...
BreakFun: Jailbreaking LLMs via Schema Exploitation
arXiv:2510.17904v2 Announce Type: replace-cross Abstract: The proficiency of Large Language Models (LLMs) in processing structured...
Brain-Grounded Axes for Reading and Steering LLM States
arXiv:2512.19399v1 Announce Type: cross Abstract: Interpretability methods for large language models (LLMs) typically derive directions...
Brain-computer interface trials are taking off
This week, I covered the story of Casey Harrell—a man with ALS who is “the...
BrailleLLM: Braille Instruction Tuning with Large Language Models for Braille Domain Tasks
arXiv:2510.18288v1 Announce Type: new Abstract: Braille plays a vital role in education and information accessibility...
Bootstrapping Referring Multi-Object Tracking
arXiv:2406.05039v2 Announce Type: replace-cross Abstract: Referring understanding is a fundamental task that bridges natural language...
BOND 2025 AI Trends Report Shows AI Ecosystem Growing Faster than Ever with Explosive User and Developer Adoption
BOND’s latest report on Trends – Artificial Intelligence (May 2025) presents a comprehensive data-driven snapshot...
BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset
arXiv:2507.03483v2 Announce Type: replace Abstract: In this paper, we introduce BMMR, a large-scale bilingual, multimodal...
BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech
arXiv:2607.06054v1 Announce Type: cross Abstract: Off-the-shelf TTS systems are poorly adapted to Taiwanese Mandarin. Their...
BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity
arXiv:2507.08771v1 Announce Type: cross Abstract: To alleviate the computational burden of large language models (LLMs)...
BlackboxNLP-2025 MIB Shared Task: Exploring Ensemble Strategies for Circuit Localization Methods
arXiv:2510.06811v1 Announce Type: new Abstract: The Circuit Localization track of the Mechanistic Interpretability Benchmark (MIB)...
