9 papers
GigaSpeechBench: A Real-World Multilingual Speech-to-Text Benchmark
Yujie Tu, Yifan Yang, Tianrui Wang +35
While modern ASR systems achieve low error rates on high-resource benchmarks, such performance often overestimates real-world robustness. Existing evaluations address challenges in…
The Verification Horizon: No Silver Bullet for Coding Agent Rewards
Binghai Wang, Chenlong Zhang, Dayiheng Liu +10
A classical intuition holds that verifying a solution is easier than producing one. For today's coding agents, this intuition is being inverted: as foundation models develop strong…
CulMind: Benchmarking Multimodal Understanding and Reasoning in Chinese Cultural Heritage
Zhangwei Cao, Shuhan Fan, Yuting Wei +5
Evaluating Multimodal Large Language Models (MLLMs) in Chinese Cultural Heritage (CCH) requires fine-grained reasoning over visual, textual, stylistic, and historical clues. Howeve…
Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment
Wen Yang, Junhong Wu, Chen Wang +2
Direct Preference Optimization (DPO) has become a prominent method for aligning Large Language Models (LLMs) with human preferences. While DPO has enabled significant progress in a…
Language Imbalance Driven Rewarding for Multilingual Self-improving
Wen Yang, Junhong Wu, Chen Wang +2
Large Language Models (LLMs) have achieved state-of-the-art performance across numerous tasks. However, these advancements have predominantly benefited "first-class" languages such…
Hit the Sweet Spot! Span-Level Ensemble for Large Language Models
Yangyifan Xu, Jianghao Chen, Junhong Wu +1
Ensembling various LLMs to unlock their complementary potential and leverage their individual strengths is highly valuable. Previous studies typically focus on two main paradigms:…
BLSP-Emo: Towards Empathetic Large Speech-Language Models
Chen Wang, Minpeng Liao, Zhongqiang Huang +3
The recent release of GPT-4o showcased the potential of end-to-end multimodal models, not just in terms of low latency but also in their ability to understand and generate expressi…
Diver: Large Language Model Decoding with Span-Level Mutual Information Verification
Jinliang Lu, Chen Wang, Jiajun Zhang
Large language models (LLMs) have shown impressive capabilities in adapting to various tasks when provided with task-specific instructions. However, LLMs using standard decoding st…
BLSP-KD: Bootstrapping Language-Speech Pre-training via Knowledge Distillation
Chen Wang, Minpeng Liao, Zhongqiang Huang +1
Recent end-to-end approaches have shown promise in extending large language models (LLMs) to speech inputs, but face limitations in directly assessing and optimizing alignment qual…