978 citations · 1.5k across the 58 of their papers we have counts for
27 papers · 1 filter
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
DeepSeek-AI, :, Anyi Xu +585
The widespread adoption of long-horizon agents has made model workloads increasingly input-heavy. Although prior work has substantially reduced the cost of long-context computation…
DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
DeepSeek-AI, Anyi Xu, Bangcai Lin +315
We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models -- DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSe…
Adam's Law: Textual Frequency Law on Large Language Models
Hongyuan Adam Lu, Z. L., Victor Wei +5
While textual frequency has been validated as relevant to human cognition in reading speed, its relatedness to Large Language Models (LLMs) is seldom studied. We propose a novel re…
.tmu: A Low-Entropy Tree-Structured Representation for LLM-Assisted Scientific Writing
Tianyou Liu, Ziqiang Li, Xurui Liu +2
As large language models (LLMs) increasingly assist scientific writing, the limitations and token costs of generating TeX become increasingly visible. This paper analyzes TeX's arc…
DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
DeepSeek-AI, Aixin Liu, Aoxue Mei +260
We introduce DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance. The key technical breakthroughs of DeepSeek-V3.2 ar…
Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning
Ran Xu, Jingjing Chen, Jiayu Ye +4
Large Language Models (LLMs) are widely used as judges to evaluate response quality, providing a scalable alternative to human evaluation. However, most LLM judges operate solely o…
The Bias is in the Details: An Assessment of Cognitive Bias in LLMs
R. Alexander Knipper, Charles S. Knipper, Kaiqi Zhang +3
As Large Language Models (LLMs) are increasingly embedded in real-world decision-making processes, it becomes crucial to examine the extent to which they exhibit cognitive biases.…
FinanceReasoning: Benchmarking Financial Numerical Reasoning More Credible, Comprehensive and Challenging
Zichen Tang, Haihong E, Ziyan Ma +10
We introduce FinanceReasoning, a novel benchmark designed to evaluate the reasoning capabilities of large reasoning models (LRMs) in financial numerical reasoning problems. Compare…
Jailbreak Distillation: Renewable Safety Benchmarking
Jingyu Zhang, Ahmed Elgohary, Xiawei Wang +5
Large language models (LLMs) are rapidly deployed in critical applications, raising urgent needs for robust safety benchmarking. We propose Jailbreak Distillation (JBDistill), a no…
Inference-Time Scaling for Generalist Reward Modeling
Zijun Liu, Peiyi Wang, Runxin Xu +5
Reinforcement learning (RL) has been widely adopted in post-training for large language models (LLMs) at scale. Recently, the incentivization of reasoning capabilities in LLMs from…
Revisiting Classification Taxonomy for Grammatical Errors
Deqing Zou, Jingheng Ye, Yulu Liu +7
Grammatical error classification plays a crucial role in language learning systems, but existing classification taxonomies often lack rigorous validation, leading to inconsistencie…
CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction
Junlong Li, Daya Guo, Dejian Yang +3
Reasoning is a fundamental capability of Large Language Models. While prior research predominantly focuses on enhancing narrow skills like math or code generation, improving perfor…
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
DeepSeek-AI, Daya Guo, Dejian Yang +195
General reasoning represents a long-standing and formidable challenge in artificial intelligence. Recent breakthroughs, exemplified by large language models (LLMs) and chain-of-tho…
DeepSeek-V3 Technical Report
DeepSeek-AI, Aixin Liu, Bei Feng +195
We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effec…
Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling
Ziqiang Zhang, Long Zhou, Chengyi Wang +10
We propose a cross-lingual neural codec language model, VALL-E X, for cross-lingual speech synthesis. Specifically, we extend VALL-E and train a multi-lingual conditional codec lan…
SpeechLM: Enhanced Speech Pre-Training with Unpaired Textual Data
Ziqiang Zhang, Sanyuan Chen, Long Zhou +8
How to boost speech pre-training with textual data is an unsolved problem due to the fact that speech and text are very different modalities with distinct characteristics. In this…
Supervision-Guided Codebooks for Masked Prediction in Speech Pre-training
Chengyi Wang, Yiming Wang, Yu Wu +4
Recently, masked prediction pre-training has seen remarkable progress in self-supervised learning (SSL) for speech recognition. It usually requires a codebook obtained in an unsupe…
Why does Self-Supervised Learning for Speech Recognition Benefit Speaker Recognition?
Sanyuan Chen, Yu Wu, Chengyi Wang +8
Recently, self-supervised learning (SSL) has demonstrated strong performance in speaker recognition, even if the pre-training objective is designed for speech recognition. In this…
UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training
Sanyuan Chen, Yu Wu, Chengyi Wang +8
Self-supervised learning (SSL) is a long-standing goal for speech processing, since it utilizes large-scale unlabeled data and avoids extensive human labeling. Recent years witness…
Internal Language Model Adaptation with Text-Only Data for End-to-End Speech Recognition
Zhong Meng, Yashesh Gaur, Naoyuki Kanda +4
Text-only adaptation of an end-to-end (E2E) model remains a challenging task for automatic speech recognition (ASR). Language model (LM) fusion-based approaches require an addition…
Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition
Yiming Wang, Jinyu Li, Heming Wang +3
The goal of self-supervised learning (SSL) for automatic speech recognition (ASR) is to learn good speech representations from a large amount of unlabeled speech for the downstream…
Template-Based Named Entity Recognition Using BART
Leyang Cui, Yu Wu, Jian Liu +2
There is a recent interest in investigating few-shot NER, where the low-resource target domain has different label sets compared with a resource-rich source domain. Existing method…
On Commonsense Cues in BERT for Solving Commonsense Tasks
Leyang Cui, Sijie Cheng, Yu Wu +1
BERT has been used for solving commonsense tasks such as CommonsenseQA. While prior research has found that BERT does contain commonsense information to some extent, there has been…
Curriculum Pre-training for End-to-End Speech Translation
Chengyi Wang, Yu Wu, Shujie Liu +2
End-to-end speech translation poses a heavy burden on the encoder, because it has to transcribe, understand, and learn cross-lingual semantics simultaneously. To obtain a powerful…