Live intelligence

Latest AI updates

2 updates
Research

Depth as a Candidate Source: Portfolio Allocation for Recurrent Test-Time Scaling in Large Language Models

The paper analyzes recurrent latent reasoning in LLMs and finds that deeper recurrence can lose correct solutions found at shallower depths, with depth-specific success sets remaining broadly non-nested. It proposes Depth Portfolio Allocation (DPA), which treats recurrent test-time scaling as budgeted allocation across depth-specific candidate sources, supporting fixed and feedback-guided sequential allocation. Experiments on GSM8K, SVAMP, MultiArith, and MBPP indicate that mixed-depth portfolios expand oracle coverage under matched candidate counts and nominal costs, while feedback-guided allocation generally matches or improves uniform allocation and can reduce computation in high-budget settings.

test-time computeLLM reasoninginference efficiency
Research Editor selected

Dynamical Memory Transformer: Selective Recurrent Memories with Constant Cost Attention

Researchers present the Dynamical Memory Transformer (DMT), a hybrid architecture that separates sequence encoding from information reading. Several memory units, each a dynamical system with a complex diagonal recurrent matrix and an input-dependent leak rate, are read by attention without going through token history. The recurrence supports an associative scan with O(T) total work and O(log T) parallel depth, while recurrent states and the convolution cache remain fixed-size during autoregressive inference. Experiments show gains on several cognitive tasks and stronger length extrapolation on selective copy, with language-modeling performance close to Transformer but behind Mamba.

Why it matters: It offers a concrete architectural alternative for constant-cost long-context inference, with candid comparisons against Transformer and Mamba.

Dynamical Memory TransformerEfficient attentionLong-context modeling