ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

~ similar to 2605.31432· 12 results

cs.CLcs.AIeess.ASRecentMay 31, 2026

PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects

Sicheng Yang, Shulan Ruan, Shiwei Wu, Yu Liu +3 more

PolySpeech-100 introduces a massive, multi-lingual benchmark covering 110 linguistic variants to rigorously test Speech-LLMs, demonstrating that open-source models struggle with low-resource languages…

View →
cs.AIRecentMay 28, 2026

Entropy-KL Divergence-based Token Masking: A Novel Approach for Selective Fine-tuning of Large Language Models

Qi Liu, Mingdi Sun, Yongyi He, Zhi Zheng +4 more

The paper proposes EKSFT, a selective fine-tuning method that masks high-entropy or high-KL divergence tokens during Supervised Fine-Tuning (SFT) to prevent distribution shift and improve subsequent R…

View →
cs.CLeess.ASRecentMay 30, 2026

SALSA: Speech Aware LLM Adaptation via Learned Steering Activation Vectors

Yekaterina Yegorova, Argyrios Gerogiannis, Haolong Zheng, Julia Hockenmaier +2 more

SALSA is a lightweight adaptation method that learns layer-wise steering vectors to significantly improve the performance of speech-aware LLMs on out-of-domain speech tasks.

View →
cs.CRRecentJun 3, 2026

Attention-Augmented LSTMs for Automatic Homophonic Ciphertext Decipherment

Micaella Bruton, Meriem Beloucif, Beáta Megyesi

The paper demonstrates that an attention-augmented LSTM model can achieve near-perfect character-level decipherment of homophonic ciphertexts from historical English and Swedish, even under challengin…

View →
cs.AIcs.CLcs.LGRecentJun 1, 2026

Forget Attention: Importance-Aware Attention Is All You Need

Soohyeong Shin, Yeongwook Yang

The paper proposes SISA (SSM-Informed Softmax Attention), a novel hybrid attention mechanism that integrates state-space model (SSM) importance signals directly into the attention score, achieving sta…

View →
cs.LGcs.AIcs.CLRecentMay 27, 2026

Parallax: Parameterized Local Linear Attention for Language Modeling

Yifei Zuo, Dhruv Pai, Zhichen Zeng, Alec Dewulf +2 more

The paper introduces Parallax, a scalable and numerically stable parameterized Local Linear Attention mechanism that significantly improves LLM performance and efficiency compared to existing methods…

View →
cs.AIcs.CVeess.ASRecentMay 27, 2026

Diffusion Large Language Models for Visual Speech Recognition

Jeong Hun Yeo, Chae Won Kim, Hyeongseop Rha, Yong Man Ro

The paper proposes DLLM-VSR, a novel Diffusion Large Language Model framework for Visual Speech Recognition, achieving state-of-the-art performance by treating transcription as iterative masked denois…

View →
cs.SDcs.AIeess.ASRecentMay 29, 2026

Chatterbox-Flash: Prior-Calibrated Block Diffusion for Streaming Zero-Shot TTS

Deokjin Seo, Gangin Park, Kihyun Nam

Chatterbox-Flash introduces a prior-calibrated block diffusion model for zero-shot TTS that achieves high-fidelity, streaming synthesis with significantly lower computational overhead than existing me…

View →
cs.AIRecentMay 28, 2026

Moment-KV: Momentum-Based Decode-Time KV Cache Compression for Long Generation

Soumyadeep Jana, Sagar Nishad, Sanasam Ranbir Singh

Moment-KV introduces a novel momentum-based technique to compress the Key-Value (KV) cache during the decoding phase of LLM generation, significantly improving fidelity in long-generation tasks.

View →
cs.CLcs.AIRecentMay 27, 2026

KVoiceBench, KOpenAudioBench, and KMMAU: Agent-Driven Korean Speech Benchmarks for Evaluating SpeechLMs

Haechan Kim, Seungjun Chung, Inkyu Park, Jihoo Lee +1 more

The paper introduces three new Korean speech benchmarks (KVoiceBench, KOpenAudioBench, and KMMAU) to evaluate SpeechLMs, demonstrating that English-centric evaluation fails to capture performance gaps…

View →
cs.CLcs.AIRecentMay 31, 2026

Hybrid Verified Decoding: Learning to Allocate Verification in Speculative Decoding

Xin Su, Dawid Majchrowski, Fangyuan Yu, Vanshil Atul Shah +4 more

The paper introduces Hybrid Verified Decoding, a method that predicts the acceptance length of a cache draft to intelligently select between cache verification and model-based drafting, achieving sign…

View →
cs.LGcs.AIcs.DCRecentMay 27, 2026

How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving

Hanjiang Wu, Abhimanyu Rajeshkumar Bambhaniya, Sarbartha Banerjee, Tuhin Khare +8 more

The paper systematically analyzes the benefits and limits of Attention-FFN Disaggregation (AFD) for Mixture-of-Experts (MoE) LLM serving, demonstrating that AFD is crucial for achieving high throughpu…

View →