💾 CPU Caching - emschwartz · Scour

Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs 💉Prompt Injection

VG-CoT: Towards Trustworthy Visual Reasoning via Grounded Chain-of-Thought ✨Gemini

C-Mining: Unsupervised Discovery of Seeds for Cultural Data Synthesis via Geometric Misalignment 🐘pgvector

Harmful Intent as a Geometrically Recoverable Feature of LLM Residual Streams 🛡️AI Safety

Continual Safety Alignment via Gradient-Based Sample Selection 🛡️AI Safety

On the Rejection Criterion for Proxy-based Test-time Alignment 🚩CTF Writeups

When Choices Become Risks: Safety Failures of Large Language Models under Multiple-Choice Constraints 🛡️AI Safety

SafeAnchor: Preventing Cumulative Safety Erosion in Continual Domain Adaptation of Large Language Models 🛡️AI Safety

Evolutionary Negative Module Pruning for Better LoRA Merging 🧠LLM Inference

Demystifying the unreasonable effectiveness of online alignment methods 🔍Vector Search Algorithms

Spec2Cov: An Agentic Framework for Code Coverage Closure of Digital Hardware Designs 💻Coding Agents

CGCMA: Conditionally-Gated Cross-Modal Attention for Event-Conditioned Asynchronous Fusion 🧠LLM Inference

An Empirical Study of Multi-Generation Sampling for Jailbreak Detection in Large Language Models 🔤Tokenization

Guardrails in Logit Space: Safety Token Regularization for LLM Alignment 🛡️AI Safety

Self-Improving Tabular Language Models via Iterative Group Alignment 📊Vector Databases

Towards Robust Endogenous Reasoning: Unifying Drift Adaptation in Non-Stationary Tuning 🧠LLM Inference

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference 🧠LLM Inference

A Systematic Study of Training-Free Methods for Trustworthy Large Language Models 🧠LLM Inference

Concept-wise Attention for Fine-grained Concept Bottleneck Models 🧠LLM Inference

Certified Program Synthesis with a Multi-Modal Verifier 📐TLA+

Log in to enable infinite scrolling