#representation-analysis News & Analysis

4 articles tagged with #representation-analysis. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

4 articles

AINeutralarXiv – CS AI · May 296/10

🧠

VLA-Trace: Diagnosing Vision-Language-Action Models through Representation and Behavior Tracing

Researchers introduce VLA-Trace, a diagnostic framework for analyzing Vision-Language-Action models that reveals how these AI systems transform multimodal inputs into physical control actions. The study identifies that popular VLA models like π₀.₅ and OpenVLA exhibit distinct adaptation patterns, rely on different routing strategies during decision-making, but struggle with fine-grained semantic understanding despite excelling at visual grounding.

AINeutralarXiv – CS AI · May 296/10

🧠

LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training

Researchers introduce LaRA, a framework for detecting data contamination in reinforcement learning post-trained large language models by analyzing layer-wise representations. The method identifies contamination through geometric deviations across neural network layers, outperforming existing detection approaches that rely on output-level signals unreliable for RL-trained models.

AINeutralarXiv – CS AI · May 286/10

🧠

When Think-with-Image Meets Safety: What Determines Multimodal Jailbreak Robustness?

Researchers demonstrate that explicit image-tool interaction in vision-language models reduces jailbreak success rates by approximately 30% compared to direct response generation. The protective effect stems from a safety-relevant shift in hidden representations rather than benign image semantics alone, suggesting image-tool invocation is a promising architectural pattern for improving multimodal AI safety.

AINeutralarXiv – CS AI · May 126/10

🧠

Belief or Circuitry? Causal Evidence for In-Context Graph Learning

Researchers present causal evidence that large language models learn in-context through dual mechanisms combining genuine structure inference with local pattern-matching, rather than relying on either approach alone. Using graph random-walk tasks and activation patching techniques, they demonstrate that LLMs simultaneously encode multiple competing graph topologies in orthogonal representational subspaces and show that late-layer circuits causally drive graph-preference predictions.