会员服务
Sparsity-Aware Streaming SNN Accelerator with Output-Channel Dataflow for Automatic Modulation Classification
Arxiv
0+阅读 · 1月6日
Copyright Laundering Through the AI Ouroboros: Adapting the 'Fruit of the Poisonous Tree' Doctrine to Recursive AI Training
Arxiv
0+阅读 · 1月6日
Successive classification learning for estimating quantile optimal treatment regimes
Arxiv
0+阅读 · 1月6日
Linear Script Representations in Speech Foundation Models Enable Zero-Shot Transliteration
Arxiv
0+阅读 · 1月6日
When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent Reasoning
Arxiv
0+阅读 · 1月5日
Prompt-Counterfactual Explanations for Generative AI System Behavior
Arxiv
0+阅读 · 1月6日
Intervene-All-Paths: Unified Mitigation of LVLM Hallucinations across Alignment Formats
Arxiv
0+阅读 · 1月6日
BaseCal: Unsupervised Confidence Calibration via Base Model Signals
Arxiv
0+阅读 · 1月6日
Empowering Reliable Visual-Centric Instruction Following in MLLMs
Empowering Reliable Visual-Centric Instruction Following in MLLMs
Arxiv
0+阅读 · 1月6日
Output Embedding Centering for Stable LLM Pretraining
Arxiv
0+阅读 · 1月5日
On LLMs' Internal Representation of Code Correctness
Arxiv
0+阅读 · 1月5日
Project Ariadne: A Structural Causal Framework for Auditing Faithfulness in LLM Agents
Project Ariadne: A Structural Causal Framework for Auditing Faithfulness in LLM Agents
Arxiv
0+阅读 · 1月5日
SteganoBackdoor: Stealthy and Data-Efficient Backdoor Attacks on Language Models
SteganoBackdoor: Stealthy and Data-Efficient Backdoor Attacks on Language Models
Arxiv
0+阅读 · 1月5日
FaithLens: Detecting and Explaining Faithfulness Hallucination
Arxiv
0+阅读 · 1月5日
Beyond Prompts: Space-Time Decoupling Control-Plane Jailbreaks in LLM Structured Output
Arxiv
0+阅读 · 1月5日
参考链接
微信扫码咨询专知VIP会员
Top