When Does LLM Reasoning Help Recommendation? The Semantic Richness Index
A cross-domain study: LLMs improve recommendation only when SRI >= 0.45 (semantic-rich content). On…
A cross-domain study: LLMs improve recommendation only when SRI >= 0.45 (semantic-rich content). On…
Applying GC principles (reference counting, generational collection, memory pools) to GPU memory in…
A five-layer (L0-L4) citation verification engine: L2 semantic claim verification achieves 93.5% ac…
RecCache transfers the draft-and-verify paradigm from speculative LLM decoding to recommendation ca…
Systemic financial risk is predicted by high-density market states — the opposite of anomaly detect…
When combining unreliable inference oracles, voting vs weighted averaging can matter 14.5x more tha…
Structural causal graph features find root causes in multi-agent LLM failures at 35ms and zero cost…
How IJCNN reviewer feedback drove fundamental improvements: from fabricated references and unclear …
The full journey of submitting the HMM-TS routing paper to ProbML 2026: from initial KDD draft to 3…