让下一篇重要论文，不再错过。

Reinforcement learning (RL) has become a standard post-training method for diffusion models, but most RL objectives roll out the current policy at every iteration, and with a many-step sampler these rollouts typically dominate the cost of training. Few-step models cut this cost, yet they model an average velocity over an interval, whereas existing RL objectives are built for an instantaneous velocity with a many-step sampler. We adapt RL objectives to few-step models systematically in three phases, namely a transformation, a decomposition and an adaptation. The transformation to $x$-space expresses each objective we consider through a common policy prediction, at the clean end by default and at an explicitly marked level for transition or flow-map objectives, so that objectives stated over densities, velocities or rewards become comparable. The decomposition writes the gradient of each of these objectives as the sum of a self-regression toward a reference and a reward augmentation, so that a method reduces, at the gradient level, to a choice of anchors and weights. The adaptation computes each anchor from a few-step model at the end of its transport or along its tangent, with the instantaneous velocity recovered from the network itself or from an auxiliary network. This yields few-step versions of FlowGRPO, AWM, DiffusionNFT, DiffusionOPSD and ReFL in one modular codebase. In our experiments, reward-gradient-based methods are the most effective when the reward is differentiable and its gradient is affordable; otherwise DiffusionNFT-style methods generally reach high rewards in relatively few iterations despite a sometimes higher per-iteration cost. Extra inference steps show no systematic aggregate benefit in our experiments, although selected outputs visibly improve with two to four times as many sampling steps as in training.

We investigate the optimal asymptotic rate $R_q$ of perfect $q$-hash codes, a fundamental extremal problem in combinatorics, information theory, and computer science. Let $B_q=-\log_2(1-q!/q^q)/(q-1)$ denote the classical probabilistic lower bound. We prove that $R_q=B_q$ if and only if $q=2$, establishing an explicit strict improvement for every $q\ge3$ and settling the first assertion of a conjecture of Xing and Yuan (Combinatorica 43 (2023), 347--366). More significantly, we show that, for every $η>0$, $R_q\ge B_q+\exp(-(2+η)q)$ for all sufficiently large integers $q$. This improves the previously known increments of scale $\exp(-3q+O(\ln q))$ by an exponential factor. We also establish a structural limitation of the concatenation method. For pairwise uniform inner codes of subexponential length, the resulting rate bound exceeds $B_q$ by at most $\exp(-3q+o(q))$. Thus, exponentially long inner codes are necessary to achieve the new improvement scale within this framework. Our proofs combine Fourier analysis, high-dimensional simplex codes, additive permutation counts, and entropy bounds for hypergraph matchings. We further strengthen lower bounds from short inner codes and improve several known numerical estimates.

Quantum locally recoverable codes (qLRCs) are a class of quantum error-correcting codes that can recover an erased qudit by accessing only a few other qudits. This paper develops a general framework for constructing optimal pure qLRCs that attain the Plotkin-like bound, referred to as Plotkin-optimal pure qLRCs, from Hermitian dual-containing near maximum-distance separable (NMDS) codes. Focusing on a special class of NMDS codes called extended subcodes of generalized Reed-Solomon (ESGRS) codes, we determine their localities by analyzing certain subset sum problems over finite fields. By further exploiting the algebraic structures of ESGRS codes and related codes, we construct four families of Plotkin-optimal pure qLRCs with large lengths and more flexible minimum distances than existing constructions. These constructions provide strong global error-correction capability while retaining local recovery. To the best of our knowledge, they give the first families of qLRCs attaining the pure Plotkin-like bound. In addition, by using the resulting locality property, we resolve in the negative a related problem on ESGRS codes supporting combinatorial designs.