会员服务
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
Anything Goes? A Crosslinguistic Study of (Im)possible Language Learning in LMs
Arxiv
0+阅读 · 6月13日
Different Layers, Different Manifolds: Module-Wise Weight-Space Geometry in Transformer Optimization
Arxiv
0+阅读 · 6月11日
SymbolicLight V1: Spike-Gated Dual-Path Language Modeling with High Activation Sparsity and Sub-Billion-Scale Pre-Training Evidence
Arxiv
0+阅读 · 5月20日
Probe-Geometry Alignment: Erasing the Cross-Sequence Memorization Signature Below Chance
Arxiv
0+阅读 · 5月7日
Probe-Geometry Alignment: Erasing the Cross-Sequence Memorization Signature Below Chance
Arxiv
0+阅读 · 5月6日
Darkness Visible: Reading the Exception Handler of a Language Model
Arxiv
0+阅读 · 4月7日
Biasless Language Models Learn Unnaturally: How LLMs Fail to Distinguish the Possible from the Impossible
Arxiv
0+阅读 · 3月31日
Variance Is Not Importance: Structural Analysis of Transformer Compressibility Across Model Scales
Arxiv
0+阅读 · 4月22日
Capability-Guided Compression: Toward Interpretability-Aware Budget Allocation for Large Language Models
Capability-Guided Compression: Toward Interpretability-Aware Budget Allocation for Large Language Models
Arxiv
0+阅读 · 3月17日
GPUTOK: GPU Accelerated Byte Level BPE Tokenization
Arxiv
0+阅读 · 3月3日
The Anxiety of Influence: Bloom Filters in Transformer Attention Heads
Arxiv
0+阅读 · 2月19日
Large Language Models and Impossible Language Acquisition: "False Promise" or an Overturn of our Current Perspective towards AI
Arxiv
0+阅读 · 2月17日
参考链接
微信扫码咨询专知VIP会员
Top