会员服务
AlignSAE: Concept-Aligned Sparse Autoencoders
Arxiv
0+阅读 · 10月15日
Writability and the Pathway: A Controlled Study of Knowledge Injection into Addressed Memory
Arxiv
0+阅读 · 10月15日
Efficient Long-Horizon Learning for Learned Optimization
Arxiv
0+阅读 · 10月10日
Training Leaves Traces: Centered Residual Signatures for Language Model Lineage Verification
Arxiv
0+阅读 · 9月22日
Stochastic Rounding in Low-Precision Transformer Inference: A Variable-Precision Emulation Study of a Small GPT-2
Arxiv
0+阅读 · 10月8日
Stochastic Rounding in Low-Precision Transformer Inference: A Variable-Precision Emulation Study of a Small GPT-2
Arxiv
0+阅读 · 10月1日
Harm Laundering in GPT Models: Evidence That Gender Discrimination Is Transformed Rather Than Reduced Across Safety-Trained Generations
Arxiv
0+阅读 · 9月17日
Training Leaves Traces: Centered Residual Signatures for Language Model Lineage Verification
Arxiv
0+阅读 · 8月14日
Disentangling Feature Structure: A Mathematically Provable Two-Stage Training Dynamics in Transformers
Arxiv
0+阅读 · 7月11日
Memory Depth, Not Memory Access: Selective Parametric Consolidation for Long-Running Language Agents
Arxiv
0+阅读 · 6月25日
SCIT: Testing Causal Cache Carriers in Latent Chain-of-Thought Models
SCIT: Testing Causal Cache Carriers in Latent Chain-of-Thought Models
Arxiv
0+阅读 · 8月27日
Watching Synthetic Videos: Aligning Cross-modal Representations with Visual Synthesis for Zero-shot Video Captioning
Arxiv
0+阅读 · 8月11日
First-Token Broadcasters: Mechanistic Origins of Language Identity and Distributed Robustness in Transformers
Arxiv
0+阅读 · 6月21日
Keyless Attention: Value-Space Routing and Value-Only Caching for Efficient Transformers
Arxiv
0+阅读 · 6月20日
Bifrost: Hybrid TEE-FHE Inference for Privacy-Preserving Transformer and LLM Serving
Arxiv
0+阅读 · 6月16日
参考链接
微信扫码咨询专知VIP会员
Top