Malicious LLM API routers actively perform payload injection and secret exfiltration, with 9 of 428 tested routers showing malicious behavior and further poisoning risks from leaked credentials.
BPE-Dropout: Simple and Effective Subword Regularization
7 Pith papers cite this work. Polarity classification is still indexing.
citation-role summary
citation-polarity summary
verdicts
UNVERDICTED 7roles
background 2polarities
background 2representative citing papers
TIDAL recovers temporal phase signals from LLM-derived semantics of provisioning metadata to enable complementary CVD placement, reducing overload frequency by 79.1% on production traces.
Byte-level simulations show subword tokenization improves LLM training mainly via increased throughput and boundary priors.
Sparsity-guided distillation enables replacing attention layers in ViTs with simpler sequential modules, with sparser layers showing smaller performance drops.
Lightweight proxy models deliver over 100x cost and latency savings for semantic AI queries in databases with accuracy preserved or improved on benchmarks up to 10M rows.
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
A literature survey that categorizes high-level abstract concept image classification tasks in CV into semantic clusters and identifies persistent challenges and opportunities for hybrid AI approaches.
citing papers explorer
-
Your Agent Is Mine: Measuring Malicious Intermediary Attacks on the LLM Supply Chain
Malicious LLM API routers actively perform payload injection and secret exfiltration, with 9 of 428 tested routers showing malicious behavior and further poisoning risks from leaked credentials.
-
TIDAL: Recovering Temporal Phase for Cloud Block Storage Placement from LLM-Derived Semantics
TIDAL recovers temporal phase signals from LLM-derived semantics of provisioning metadata to enable complementary CVD placement, reducing overload frequency by 79.1% on production traces.
-
Decoupling the Benefits of Subword Tokenization for Language Model Training via Byte-level Simulation
Byte-level simulations show subword tokenization improves LLM training mainly via increased throughput and boundary priors.
-
From Sparsity to Simplicity: Enabling Simpler Sequential Replacements via Sparse Attention Distillation
Sparsity-guided distillation enables replacing attention layers in ViTs with simpler sequential modules, with sparser layers showing smaller performance drops.
-
100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models
Lightweight proxy models deliver over 100x cost and latency savings for semantic AI queries in databases with accuracy preserved or improved on benchmarks up to 10M rows.
-
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
-
Seeing the Intangible: Survey of Image Classification into High-Level and Abstract Categories
A literature survey that categorizes high-level abstract concept image classification tasks in CV into semantic clusters and identifies persistent challenges and opportunities for hybrid AI approaches.