Reranking is a combinatorial decision problem that aims to select and order a high-utility slate from a request-specific candidate set. A major line of generative rerankers adopts autoregressive (AR) models, which construct the slate one position at a time to capture inter-position dependencies. However, under practical greedy or bounded-width decoding, prefix-based search may prematurely prune globally promising permutations and incurs inherently sequential latency, restricting the effective search space under a fixed serving budget. Non-autoregressive (NAR) alternatives alleviate this efficiency bottleneck through position-parallel prediction, but naive position-wise factorization treats different positions too independently, leading to insufficient cross-position coordination and potentially duplicate or conflicting item selections. To retain parallel efficiency while introducing global structural coordination, we propose Dynamic Index-based RECommendation with Transport-Optimized Retrieval (DIRECTOR), a transport-guided parallel reranking framework. DIRECTOR maps candidate items into a continuous latent space and generates request-conditioned dynamic retrieval indices for all target positions in parallel. During training, it uses entropy-regularized OT to provide conflict-aware supervision; at inference, it directly performs global hard matching on similarity matrix, producing duplicate-free slates without iterative transport. To further align the generator with an opaque list-wise evaluator that returns only a scalar utility, we introduce a prefix-anchored credit assignment mechanism that converts the global reward into position-specific training signals. Extensive offline and online experiments demonstrate that DIRECTOR consistently outperforms strong reranking baselines, achieving significant improvement in large-scale industrial recommendation scenarios.
Yuanhao Pu, Chenghao Zhang, Chao Feng et al.· 0 citations
Key-Value (KV) cache eviction—which retains the KV pairs of the most important tokens while discarding less important ones—is a critical technique for optimizing both memory usage and inference latency in large language models (LLMs). However, existing approaches often rely on simple heuristics—such as attention weights—to measure token importance, overlooking the spatial relationships be-tween token value states in the vector space. This often leads to suboptimal token selections and thus performance degradation. To tackle this problem, we propose a novel method, namely AnDPro ( An chor D irection Pro jection), which introduces a projection-based scoring function to more accurately measure token importance. Specifically, AnDPro operates in the space of value vectors and leverages the projections of these vectors onto an “Anchor Direction” —the direction of the pre-eviction output—to measure token importance and guide more accurate token selection. Experiments on 16 datasets from the LongBench benchmark demonstrate that AnDPro can maintain 96 . 07% of the full cache accuracy using only 3 . 44% KV cache budget, reducing KV cache budget size by 46 . 0% without compromising quality compared to previous state-of-the-arts.
Zijie Geng, Jie Wang, Ziqi Liu et al.· Advances in Neural Informati...· 6 citations
On-policy distillation (OPD) transfers teacher capabilities by supervising trajectories sampled from the student's own policy, yet its generalization behavior remains poorly understood, as most studies evaluate OPD on a single domain and on benchmarks close to the training data. We present a controlled study that varies one generalization factor at a time, from in-domain distribution shifts to cross-domain transfer and the multi-teacher setting. We find that OPD transfers a teacher's reasoning behavior rather than its answers to particular problems: training difficulty barely matters, and even problems the teacher never solves are useful. Transfer depends strongly on the origin relationship between teacher and student: same-origin pairs bring the student close to the teacher across languages, reasoning horizons, and even other domains, whereas cross-origin pairs mostly fit the trained distribution. This broad reach is a double-edged sword: since routing prompts to domain experts cannot confine each teacher's influence, combining them yields a mixture-dependent seesaw among their capabilities. These results clarify when OPD generalizes and offer a useful perspective for diagnosing multi-teacher OPD.
Zhaoyi Li, Deyang Kong, Yuan Wei et al.· 0 citations
Can large language models with substantially different parameter spaces be merged by direct weighted averaging, without training or semantic alignment? Existing heterogeneous fusion methods typically introduce distillation, adapters, learned latent spaces, routing, or feature alignment, leaving open whether a simpler recipe can work for genuinely different billion-parameter checkpoints. We revisit this counterintuitive question through training-free dimensional adaptation followed by ratio-controlled interpolation. In union-style merging, we expand the smaller model into the larger parameter space; in intersection-style merging, we truncate the larger model into the smaller parameter space. Across Qwen-family model pairs and benchmarks covering mathematical reasoning, code generation, language understanding, commonsense reasoning, knowledge, and instruction following, deterministic expansion largely preserves the source model function, and small-ratio interpolation can improve over strong source checkpoints by transferring complementary capabilities. However, near-balanced interpolation often collapses, and task-level results reveal a seesaw effect in which gains on some capabilities coexist with regressions on others. These results show that simple parameter averaging, when paired with lightweight dimensional adaptation and carefully controlled ratios, is a surprisingly strong baseline for heterogeneous LLM merging, suggesting that the limits of direct weighted fusion may also bound what more complex heterogeneous merging methods can achieve at scale.
Jiahe Fan, Yinghao Hou, Sixiang Chen et al.· 0 citations
Modern industrial recommender systems have increasingly adopted the Generator-Evaluator (G-E) framework for the re-ranking stage. Within this paradigm, the generator produces candidate item lists from a pool filtered by upstream retrieval and ranking modules, while the evaluator scores these lists and selects the highest-scoring one for final exposure per request. However, on sequential platforms (e.g., short-video apps), users consume items continuously, ignoring artificial list boundaries. Conventional evaluators score lists by aggregating point-wise values, implicitly assuming exposure independence. This fails to capture critical session-level dynamics, such as contextual dependencies, user continuation, and diminishing marginal utility from repetitive content. To bridge this gap, we propose SWIM (Step-Wise Integrated Measure), a list-level evaluator that models user behaviors as a finite-horizon prefix session-level survival process. SWIM estimates the prefix-conditioned contribution of the current list to the session-level objective by factorizing it into a recursive survival distribution and reached-position conditional rewards. Leveraging a causally-masked Transformer, SWIM efficiently estimates continuation probabilities and utilities in parallel, satisfying strict industrial latency constraints. Extensive experiments demonstrate that SWIM significantly outperforms baselines in listwise reranking tasks, yielding substantial improvements in overall recommendation engagement.
Yuan Pu, Chenghao Zhang, Chao Feng et al.· 0 citations
The O1 Embedder is proposed, a novel approach aiming to endow retrieval models with similar capabilities to address challenges like multi-task retrieval, zero-shot retrieval, and tasks requiring intensive reasoning of complex relationships.
Ruiran Yan, Wen Xiong, Ze Liu et al.· Annual Meeting of the Associ...· 2 citations