13 papers
When Cosine Similarity Fails to Reflect Linearly Accessible Structure in Dialogue Models
Yu Sun, Mengyin Lu, Cong Feng +2
Cosine similarity is widely used to analyze transformer representations, implicitly assuming that similarity reflects task-relevant structure. We study when this assumption fails i…
K/V-Cache Interventions Dissociate Representation Alignment from Persona Expression in Decoder-Only Language Models
Yu Sun, Mengyin Lu, Cong Feng +2
We study K/V-cache interventions -- transplanting a target-conditioned K/V trajectory into a source-persona generation -- as a structured surface for persona control in decoder-onl…
XPolicyLab: A Unified Standard and Open Ecosystem for Robot Policy Evaluation and Deployment
XPolicyLab Community, Tianxing Chen, Yue Chen +67
Robot policy evaluation and deployment remain fragmented by model-specific software dependencies, data representations, and runtime interfaces, so that connecting N policies to M e…
Intern-S2-Preview: Scientific Agentic Foundation Model
Lei Bai, Jiaqi Cao, Chiyu Chen +121
Scientific discovery increasingly requires AI systems that can reason over scientific evidence of heterogeneous modalities, interact with scientific tools and environments, and sus…
OpenCompass: A Universal Evaluation Platform for Large Language Models
Maosong Cao, Kai Chen, Haodong Duan +27
In recent years, the field of artificial intelligence has undergone a paradigm shift from task-specific small-scale models to general-purpose large language models (LLMs). With the…
Action-Prior Denoising for Smooth Real-Time Chunking
Dongyang Liu, Zhaowen Zheng, Yu Sun +3
Real-time chunking (RTC) lets chunked action policies operate under inference delay by conditioning a newly generated action chunk on actions already committed by the previous chun…
Latent Action Reparameterization for Efficient Agent Inference
Wenhao Huang, Qingwen Zeng, Qiyue Chen +11
Large language model (LLM) agents often rely on long sequences of low-level textual actions, resulting in large effective decision horizons and high inference cost. While prior wor…
SPEAR: Code-Augmented Agentic Prompt Optimization
Mengyin Lu, Cong Feng, Huimin Han +6
Automatic prompt engineering (APE) rewrites prompts to improve downstream task performance, but existing APE loops treat the optimizer itself as a fixed pipeline. We port the code-…
Sparse Growing Transformer: Training-Time Sparse Depth Allocation via Progressive Attention Looping
Yao Chen, Yilong Chen, Yinqi Yang +9
Existing approaches to increasing the effective depth of Transformers predominantly rely on parameter reuse, extending computation through recursive execution. Under this paradigm,…
KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance
Linhao Yu, Tianmeng Yang, Siyu Ding +8
RLVR improves reasoning in large language models, but its effectiveness is often limited by severe reward sparsity on hard problems. Recent hint-based RL methods mitigate sparsity…
Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale
Yicheng Zou, Dongsheng Zhu, Lin Zhu +174
We introduce Intern-S1-Pro, the first one-trillion-parameter scientific multimodal foundation model. Scaling to this unprecedented size, the model delivers a comprehensive enhancem…
ATTNPO: Attention-Guided Process Supervision for Efficient Reasoning
Shuaiyi Nie, Siyu Ding, Wenyuan Zhang +7
Large reasoning models trained with reinforcement learning and verifiable rewards (RLVR) achieve strong performance on complex reasoning tasks, yet often overthink, generating redu…
Extending RLVR to Open-Ended Tasks via Verifiable Multiple-Choice Reformulation
Mengyu Zhang, Siyu Ding, Weichong Yin +2
Reinforcement Learning with Verifiable Rewards(RLVR) has demonstrated great potential in enhancing the reasoning capabilities of large language models (LLMs). However, its success…