6 citations · 9 across the 19 of their papers we have counts for
20 papers
Safin-1: Safety from Within through Memory-Native State Evolution
Ming Zhang, Kaisen Yang, Shu Yu +15
Long-horizon complex tasks require foundation models to accumulate information, maintain internal states, and adapt over extended interactions. Safety should be an intrinsic proper…
Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoning
Kai Chen, Jifeng Ding, Ning Ding +44
We introduce Mobius-v0, an architecture that comprises a globally shared Memory (FFN) that stores knowledge vectors and multiple Reasoners (Self-Attn) that iteratively achieve comp…
MARCH: Scaling Recurrent Memory with Content-Routed State Anchors
Ming Zhang, Kaisen Yang, Shu Yu +6
Transformers owe much of their strong long-context retrieval capability to a token-level memory that grows with context length. This flexibility, however, incurs a quadratic comput…
An Early Warning of Emerging Biosecurity Risks in Frontier LLMs
Zhida He, Xia Hu, Baichen Le +20
Frontier large language models (LLMs) are increasingly integrated into scientific workflows, yet their growing biological capabilities may outpace current safeguards. To assess the…
Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering
Junlin Yang, Che Jiang, Yu Fu +21
Recursive self-improvement (RSI) requires AI systems that improve the process of building AI (i.e., AI4AI); machine learning engineering (MLE) offers a concrete, executable testbed…
Post-Trained MoE Can Skip Half Experts via Self-Distillation
Xingtai Lv, Li Sheng, Kaiyan Zhang +12
Mixture-of-Experts (MoE) scales language models efficiently through sparse expert activation, and its dynamic variant further reduces computation by adjusting the activated experts…
How Far Can Unsupervised RLVR Scale LLM Training?
Bingxiang He, Yuxin Zuo, Zeyuan Liu +18
Unsupervised reinforcement learning with verifiable rewards (URLVR) offers a pathway to scale LLM training beyond the supervision bottleneck by deriving rewards without ground trut…
DePass: Unified Feature Attributing by Simple Decomposed Forward Pass
Xiangyu Hong, Che Jiang, Kai Tian +4
Attributing the behavior of Transformer models to internal computations is a central challenge in mechanistic interpretability. We introduce DePass, a unified framework for feature…
A Survey of Reinforcement Learning for Large Reasoning Models
Kaiyan Zhang, Yuxin Zuo, Bingxiang He +36
In this paper, we survey recent advances in Reinforcement Learning (RL) for reasoning with Large Language Models (LLMs). RL has achieved remarkable success in advancing the frontie…
SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
Haozhan Li, Yuxin Zuo, Jiale Yu +18
Vision-Language-Action (VLA) models have recently emerged as a powerful paradigm for robotic manipulation. Despite substantial progress enabled by large-scale pretraining and super…
\texttt{RAI}: Towards Resistant and Resilient AI in an Evolving World
Youbang Sun, Xiang Wang, Jie Fu +2
In this position paper, we address the persistent gap between rapidly growing AI capabilities and lagging safety progress. Existing paradigms divide into ``Make AI Safe'', which ap…
FlowRL: Matching Reward Distributions for LLM Reasoning
Xuekai Zhu, Daixuan Cheng, Dinghuai Zhang +20
We propose FlowRL: matching the full reward distribution via flow balancing instead of maximizing rewards in large language model (LLM) reinforcement learning (RL). Recent advanced…
Towards a Unified View of Large Language Model Post-Training
Xingtai Lv, Yuxin Zuo, Youbang Sun +8
Two major sources of training data exist for post-training modern language models: online (model-generated rollouts) data, and offline (human or other-model demonstrations) data. T…
OPERA: A Reinforcement Learning--Enhanced Orchestrated Planner-Executor Architecture for Reasoning-Oriented Multi-Hop Retrieval
Yu Liu, Yanbing Liu, Fangfang Yuan +6
Recent advances in large language models (LLMs) and dense retrievers have driven significant progress in retrieval-augmented generation (RAG). However, existing approaches face sig…
Automating Exploratory Multiomics Research via Language Models
Shang Qu, Ning Ding, Linhai Xie +13
This paper introduces PROTEUS, a fully automated system that produces data-driven hypotheses from raw data files. We apply PROTEUS to clinical proteogenomics, a field where effecti…
TTRL: Test-Time Reinforcement Learning
Yuxin Zuo, Kaiyan Zhang, Li Sheng +13
This paper investigates Reinforcement Learning (RL) on data without explicit labels for reasoning tasks in Large Language Models (LLMs). The core challenge of the problem is reward…
Technologies on Effectiveness and Efficiency: A Survey of State Spaces Models
Xingtai Lv, Youbang Sun, Kaiyan Zhang +8
State Space Models (SSMs) have emerged as a promising alternative to the popular transformer-based models and have been increasingly gaining attention. Compared to transformers, SS…
Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization
Ermo Hua, Che Jiang, Xingtai Lv +7
Extending the context length of Language Models (LMs) by improving Rotary Position Embedding (RoPE) has become a trend. While prior works mainly address RoPE's limitations within a…
Automating Exploratory Proteomics Research via Language Models
Ning Ding, Shang Qu, Linhai Xie +13
With the development of artificial intelligence, its contribution to science is evolving from simulating a complex problem to automating entire research processes and producing nov…
Improving LoRA in Privacy-preserving Federated Learning
Youbang Sun, Zitao Li, Yaliang Li +1
Low-rank adaptation (LoRA) is one of the most popular task-specific parameter-efficient fine-tuning (PEFT) methods on pre-trained language models for its good performance and compu…