Topic
scaling
Multi-Sequence Verifiers Cut Inference Latency in Half for LLM Reasoning
A new paper by Kim et al. introduces the Multi-Sequence Verifier (MSV), a lightweight verifier that improves calibration for parallel test-time scaling in large language models. MSV enhances best-of-N selection accuracy by up to 6% and enables early-stopping strategies that achieve the same accuracy with less than half the inference latency.
Dr-DCI: New Framework Combines Retrieval and Direct Corpus Interaction for Scalable Enterprise Search
A new research paper introduces Dr-DCI, a retriever-steered framework that scales direct corpus interaction by dynamically expanding a local workspace. Experiments show accuracy improvements up to 8.3 points over raw DCI, with stable performance from 100K to 10M documents.
Technology Why Most AI Programs Stall — and What It Will Take to Scale Them
Despite massive investment, most enterprise AI initiatives fail to move beyond pilots due to lack of organizational context. Neo4j's President and CPO explains that scaling requires context graphs that capture decision traces, not better models.