collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

Neural Quadratic Forms: A Unified Minimal Model for Sudden Learning and Scaling Laws

Liu Ziyin, Yizhou Xu, Tomaso Poggio +1

Neural networks trained by gradient descent on a smooth cost function can nevertheless learn in steps: the cost holds on long plateaus and then drops abruptly. Meanwhile, training…

cs.LG2026

Geometry of Reason: Spectral Signatures of Valid Mathematical Reasoning

Valentin Noël

Verifying whether a language model is genuinely reasoning or pattern-matching remains an open problem: learned verifiers are expensive, and output-based heuristics are brittle. We…

cs.LG2026

Spectral Guardrails for Agents in the Wild: Detecting Tool Use Hallucinations via Attention Topology

Valentin Noël

Deploying autonomous agents in the wild requires reliable safeguards against tool use failures. We propose a training free guardrail based on spectral analysis of attention topolog…

cs.LG2026

Spectral Archaeology: The Causal Topology of Model Evolution

Valentin Noël

Behavioral benchmarks tell us \textit{what} a model does, but not \textit{how}. We introduce a training-free mechanistic probe using attention-graph spectra. Treating each layer as…

cs.LG2025

HalluGraph: Auditable Hallucination Detection for Legal RAG Systems via Knowledge Graph Alignment

Valentin Noël, Elimane Yassine Seidou, Charly Ken Capo-Chichi +1

Legal AI systems powered by retrieval-augmented generation (RAG) face a critical accountability challenge: when an AI assistant cites case law, statutes, or contractual clauses, pr…

cs.LG2025

Catching Contamination Before Generation: Spectral Kill Switches for Agents

Valentin Noël

Agentic language models compose multi step reasoning chains, yet intermediate steps can be corrupted by inconsistent context, retrieval errors, or adversarial inputs, which makes p…