arXiv subjects

Tingwen Liu

Publications and source records attributed to Tingwen Liu.

At least 19 recordsLinked to original sources

arXiv2026

Memory Augmentation Unlocks Efficient Chain-of-Thought Reasoning

Large language models often rely on Chain-of-Thought (CoT) reasoning to solve complex tasks, but verbose reasoning traces introduce substantial inference overhead. CoT compression shortens generation, yet aggressive compression may disrupt logical coherence and degrade performance. We formalize this trade-off as the Context-Generation Substitution Law, where explicit reasoning context substitutes for part of decode-time generation. Based on this principle, we propose Memory-Augmented Compression, a training-free framework that constructs reusable reasoning memories from historical traces and retrieves them as prefill-side scaffolds. Rather than using raw demonstrations, these memories summarize reusable reasoning patterns, key constraints, and critical operations to compensate for information lost during compression. Experiments show that Memory consistently improves prompt-based Chain-of-Draft (CoD) compression across mathematical reasoning, complex reasoning, and science question answering tasks, yielding accuracy gains of 21.4, 28.0, 29.5, and 6.61 points over CoD on GSM8K, MATH, BBH, and MMLU-Sci, while achieving a 1.14-1.49x latency speedup latency speedup over standard CoT. Memory is also compatible with token-level, reasoning-trace-level, and inference-state compression mechanisms.

cs.CL↗

arXiv2026

Reward Guided Decoding for Generative Recommendation

Generative recommendation formulates recommendation task into an SID sequence autoregressive generation paradigm, but the decoding process is often dominated by generation likelihood. This may conflict with real-world business objectives, where high-value candidates can receive low generation probability and be pruned early during beam search. Existing reranking or training-time alignment methods either intervene too late or require costly model retraining when business preferences change. To this end, we propose \textbf{R}eward \textbf{G}uided \textbf{D}ecoding, named \textbf{RGD}, a controllable decoding framework for industrial value-oriented generative recommendation. We formulate value-guided decoding as a KL-regularized reward maximization problem, deriving a closed-form reward guided decoding distribution that principledly combines generation probability with reward signals. RGD treats the base generator as a reference policy and introduces a reward model as a test-time controller, injecting reward into each decoding step to reshape the search trajectory without retraining the generator. Extensive offline and online experiments demonstrate the effectiveness of our approach for aligning personalization and business value. RGD has been deployed on the Kuaishou platform, bringing consistent improvements in real-world recommendation scenarios.

cs.IR↗

arXiv2026

Unifying Generative Recall and Multi-Objective Ranking in a Single Decoder-Only Sequence

Modern industrial recommendation systems typically separate recall and ranking into two independent stages. Although this cascade supports corpus-level retrieval and fine-grained multi-objective scoring, it causes objective inconsistency, information loss at the candidate hand-off, and redundant user-side context computation. Meanwhile, the generative recall and ranking scaling share a common Transformer-based modeling philosophy, where architectural consistency creates a natural opportunity for unified integration. However, direct sharing remains challenging since the two tasks require different information visibility and optimization methods. Therefore, we propose \textbf{UniR$^2$}, a \textbf{Uni}fied decoder-only Transformer that unifies Generative \textbf{R}ecall and Multi-Objective \textbf{R}anking within a single heterogeneous sequence comprising user context, SID trajectory, and item features. Within this sequence, the generated trajectory serves as a representation bridge between recall and ranking, where Dual-Query Prefix-Causal Attention provides task-specific visibility. The two tasks share the base attention weights but retain separate optimization boundaries, with ranking-side LoRA preserving ranking adaptability without disrupting the generative backbone. Extensive offline experiments on large-scale industrial data demonstrate the effectiveness and efficiency of UniR$^2$ for both recall and ranking. Long-term online A/B tests on Kuaishou platform further show consistent positive gains, validating the practicality of unified model in large-scale recommendation systems.

cs.IR↗

arXiv2026

Conditional Diffusion Guided Knowledge Transfer for Multi-Domain Knowledge Graph Completion

Multi-domain knowledge graph completion (MKGC) aims to improve missing triple prediction in a target KG by transferring knowledge from other support KGs. Existing methods typically enforce consistency constraints on equivalent entities across KGs to transfer knowledge, which risks suppressing domain-specific contextual information of entities. This design can also compromise entity representation information from all KG domains, impeding performance improvements, especially in low-resource data scenarios. To address this, we pioneer a generation-based paradigm for MKGC and propose DMKGC, a conditional diffusion-guided knowledge transfer framework. Our key insight is to treat each KG as a partial view of the entity entire information, and generate informative domain-general entity embeddings through diffusion models conditioned on support KGs. Particularly, we first initialize domain-agnostic entity embeddings as prior entity embeddings, and then encode them within individual KGs. Afterward, we fuse equivalent entities from support KGs as the conditional diffusion generation guidance. We leverage the prior entity embeddings as the proxy generation objective, which ensures this conditional generation to be unbiased towards any conditioned KGs. Simultaneously, we also train the generated embeddings to be predictive across KGs, thus preserving domain-specific information. Extensive experiments on 14 KGs in 3 benchmarks demonstrate a 4.3\% average MRR improvement in tail entity prediction over state-of-the-art methods, with sustained gains in low-resource data settings.

cs.CL↗

arXiv2026

ConSA: Controllable Sparsity in Hybrid Attention via Learnable Allocation

Hybrid architectures combining full attention (FA) and sliding-window attention (SWA) are a promising paradigm for efficient LLM inference. However, existing methods typically rely on hand-crafted rules or simple post-hoc heuristics for FA/SWA allocation and offer limited analysis of the attention behaviors underlying these designs. We propose Controllable Sparsity in Hybrid Attention (ConSA), a framework that learns optimal FA/SWA assignment under a user-specified sparsity target. ConSA employs L0 regularization to learn binary masks selecting between FA and SWA for each attention unit, while an augmented Lagrangian constraint enforces the target sparsity at either layer or KV-head granularity. We evaluate ConSA on two LLMs at the 0.6B and 1.7B scales. Learned allocations consistently outperform rule-based baselines, with KV-head-wise allocation yielding clear gains over layer-wise allocation. The learned patterns place SWA in the bottom layers and concentrate FA into contiguous middle-layer blocks, diverging from evenly interleaved patterns in rule-based methods. This structure persists across model scales, sparsity levels, and allocation granularities, revealing a fine-grained spectrum of intrinsic attention behaviors that underlies the learned allocation.

cs.CL↗

arXiv2026

Beyond Patches: Superpixel Token-based Transformers for Attribute-Specific Fashion Retrieval

Attribute-Specific Fashion Retrieval (ASFR) aims to improve fine-grained image retrieval by focusing on specific attributes. However, existing patch-based attention and Transformer methods often misalign with irregular attribute regions and are prone to background noise, limiting their ability to capture subtle, pixel-level microstructures. To tackle these challenges, we propose SuperFashion, the first ASFR framework that adopts superpixel tokens within a Transformer architecture. SuperFashion initially employs an attribute-guided attention mechanism to extract attribute-related features, which in turn guide the cropping of semantically meaningful image regions. Superpixel segmentation is then leveraged on these regions to generate compact, semantically coherent superpixel tokens. By incorporating modality-specific embeddings for both attribute and superpixel tokens, the superpixel token-based Transformer facilitates adaptive interaction and fusion, thereby enhancing attribute localization and discrimination. Extensive experiments on FashionAI, DARN, and DeepFashion demonstrate relative overall MAP improvements of 1.84%, 9.27%, and 9.35% over prior SOTA. SuperFashion offers a new solution for web-based image retrieval.

cs.IR↗

arXiv2026

What If Prompt Injection Never Left? Rethinking Agent Security through Cross-Session Stored Prompt Injection

Modern agentic systems fundamentally reshape the security boundary of LLMs by introducing persistent system state including memories, filesystems, tools, and other long-lived contextual artifacts that survives across sessions. As external information crosses this boundary and becomes part of persistent agent state, malicious instructions are no longer confined to a single interaction, but can silently persist and influence future executions long after the original attacker interaction has ended. We introduce Cross-Session Stored Prompt Injection, a new threat vector inspired by stored cross-site scripting that redefines prompt injection for agentic systems by extending its threat model across both time, where attacks persist and activate across sessions, and space, where adversarial instructions propagate beyond the immediate prompt into persistent system state. To systematically characterize this emerging threat, we formalize the lifecycle of cross-session stored prompt injection, develop a taxonomy of persistence channels and incorporation mechanisms, and build a sandbox toolkit for evaluation. Our findings suggest that the fundamental challenge of agent security is not merely filtering untrusted inputs, but governing how external information acquires authority as it crosses persistent system boundaries. We hope this work motivates a broader shift from interaction-centric security toward state-centric security, making the secure management of persistent agent state a first-class security principle for the agentic era.

cs.CR↗

arXiv2026

Personalized Multi-Interest Modeling for Cross-Domain Recommendation to Cold-Start Users

Cross-domain recommendation (CDR) has demonstrated to be an effective solution for alleviating the user cold-start issue. By leveraging rich user-item interactions available in a richly informative source domain, CDR could improve the recommendation performance for cold-start users in the target domain. Previous CDR approaches mostly adhere the Embedding and Mapping (EMCDR) paradigm, which learns a user-shared mapping function to transfer users' preference from the source domain to the target domain, neglecting users' personalized preference. Recent CDR approaches further leverage the meta-learning paradigm, considering the CDR task for each user independently and learning user-specific mapping functions for each user. However, they mostly learn representations for each user individually, which ignores the common preference between different users, neglecting valuable information for CDR. In addition, all these approaches usually summarize the user's preference into an overall representation, which can hardly capture the user's multi-interest preference. To this end, we propose a personalized multi-interest modeling framework for CDR to cold-start users, termed as NF-NPCDR. Specifically, we propose a personalized preference encoder that enhances the neural process (NP) with the normalizing flow (NF) to convert the Gaussian (unimodal) distribution to a multimodal distribution, providing a novel way to capture the user's personalized multi-interest preference. Then, we propose a common preference encoder with a preference pool to capture the common preference between different users. Furthermore, we introduce a stochastic adaptive decoder to incorporate both the personalized and common preference for cold-start users, adaptively modulating both preference for better recommendation.

cs.IR↗

arXiv2026

Beyond N-gram: Data-Aware X-GRAM Extraction for Efficient Embedding Parameter Scaling

Large token-indexed lookup tables provide a compute-decoupled scaling path, but their practical gains are often limited by poor parameter efficiency and rapid memory growth. We attribute these limitations to Zipfian under-training of the long tail, heterogeneous demand across layers, and "slot collapse" that produces redundant embeddings. To address this, we propose X-GRAM, a frequency-aware dynamic token-injection framework. X-GRAM employs hybrid hashing and alias mixing to compress the tail while preserving head capacity, and refines retrieved vectors via normalized SwiGLU ShortConv to extract diverse local n-gram features. These signals are integrated into attention value streams and inter-layer residuals using depth-aware gating, effectively aligning static memory with dynamic context. This design introduces a memory-centric scaling axis that decouples model capacity from FLOPs. Extensive evaluations at the 0.73B and 1.15B scales show that X-GRAM improves average accuracy by as much as 4.4 points over the vanilla backbone and 3.2 points over strong retrieval baselines, while using substantially smaller tables in the 50% configuration. Overall, by decoupling capacity from compute through efficient memory management, X-GRAM offers a scalable and practical paradigm for future memory-augmented architectures. Code aviliable in https://github.com/Longyichen/X-gram.

cs.CL↗

arXiv2026

Unlocking the Power of Large Language Models for Multi-table Entity Matching

Multi-table entity matching (MEM) addresses the limitations of dual-table approaches by enabling simultaneous identification of equivalent entities across multiple data sources without unique identifiers. However, existing methods relying on pre-trained language models struggle to handle semantic inconsistencies caused by numerical attribute variations. Inspired by the powerful language understanding capabilities of large language models (LLMs), we propose a novel LLM-based framework for multi-table entity matching, termed LLM4MEM. Specifically, we first propose a multi-style prompt-enhanced LLM attribute coordination module to address semantic inconsistencies. Then, to alleviate the matching efficiency problem caused by the surge in the number of entities brought by multiple data sources, we develop a transitive consensus embedding matching module to tackle entity embedding and pre-matching issues. Finally, to address the issue of noisy entities during the matching process, we introduce a density-aware pruning module to optimize the quality of multi-table entity matching. We conducted extensive experiments on 6 MEM datasets, and the results show that our model improves by an average of 5.1% in F1 compared with the baseline model. Our code is available at https://github.com/Ymeki/LLM4MEM.

cs.CL↗

arXiv2026

Improving Reasoning Capabilities in Small Models through Mixture-of-Layers Distillation with Stepwise Attention on Key Information

The significant computational demands of large language models have increased interest in distilling reasoning abilities into smaller models via Chain-of-Thought (CoT) distillation. Current CoT distillation methods mainly focus on transferring teacher-generated rationales for complex reasoning to student models. However, they do not adequately explore teachers' dynamic attention toward critical information during reasoning. We find that language models exhibit progressive attention shifts towards key information during reasoning, which implies essential clues for drawing conclusions. Building on this observation and analysis, we introduce a novel CoT distillation framework that transfers the teacher's stepwise attention on key information to the student model. This establishes structured guidance for the student's progressive concentration on key information during reasoning. More importantly, we develop a Mixture of Layers module enabling dynamic alignment that adapts to different layers between the teacher and student. Our method achieves consistent performance improvements across multiple mathematical and commonsense reasoning datasets. To our knowledge, it is the first method to leverage stepwise attention within CoT distillation to improve small model reasoning.

cs.CL↗

arXiv2026

Detecting RAG Extraction Attack via Dual-Path Runtime Integrity Game

Retrieval-Augmented Generation (RAG) systems augment large language models with external knowledge, yet introduce a critical security vulnerability: RAG Knowledge Base Leakage, wherein adversarial prompts can induce the model to divulge retrieved proprietary content. Recent studies reveal that such leakage can be executed through adaptive and iterative attack strategies (named RAG extraction attack), while effective countermeasures remain notably lacking. To bridge this gap, we propose CanaryRAG, a runtime defense mechanism inspired by stack canaries in software security. CanaryRAG embeds carefully designed canary tokens into retrieved chunks and reformulates RAG extraction defense as a dual-path runtime integrity game. Leakage is detected in real time whenever either the target or oracle path violates its expected canary behavior, including under adaptive suppression and obfuscation. Extensive evaluations against existing attacks demonstrate that CanaryRAG provides robust defense, achieving substantially lower chunk recovery rates than state-of-the-art baselines while imposing negligible impact on task performance and inference latency. Moreover, as a plug-and-play solution, CanaryRAG can be seamlessly integrated into arbitrary RAG pipelines without requiring retraining or structural modifications, offering a practical and scalable safeguard for proprietary data.

cs.CR↗

arXiv2026

HyperMem: Hypergraph Memory for Long-Term Conversations

Long-term memory is essential for conversational agents to maintain coherence, track persistent tasks, and provide personalized interactions across extended dialogues. However, existing approaches as Retrieval-Augmented Generation (RAG) and graph-based memory mostly rely on pairwise relations, which can hardly capture high-order associations, i.e., joint dependencies among multiple elements, causing fragmented retrieval. To this end, we propose HyperMem, a hypergraph-based hierarchical memory architecture that explicitly models such associations using hyperedges. Particularly, HyperMem structures memory into three levels: topics, episodes, and facts, and groups related episodes and their facts via hyperedges, unifying scattered content into coherent units. Leveraging this structure, we design a hybrid lexical-semantic index and a coarse-to-fine retrieval strategy, supporting accurate and efficient retrieval of high-order associations. Experiments on the LoCoMo benchmark show that HyperMem achieves state-of-the-art performance with 92.73% LLM-as-a-judge accuracy, demonstrating the effectiveness of HyperMem for long-term conversations.

cs.CL↗

arXiv2026

Sparse Growing Transformer: Training-Time Sparse Depth Allocation via Progressive Attention Looping

Existing approaches to increasing the effective depth of Transformers predominantly rely on parameter reuse, extending computation through recursive execution. Under this paradigm, the network structure remains static along the training timeline, and additional computational depth is uniformly assigned to entire blocks at the parameter level. This rigidity across training time and parameter space leads to substantial computational redundancy during training. In contrast, we argue that depth allocation during training should not be a static preset, but rather a progressively growing structural process. Our systematic analysis reveals a deep-to-shallow maturation trajectory across layers, where high-entropy attention heads play a crucial role in semantic integration. Motivated by this observation, we introduce the Sparse Growing Transformer (SGT). SGT is a training-time sparse depth allocation framework that progressively extends recurrence from deeper to shallower layers via targeted attention looping on informative heads. This mechanism induces structural sparsity by selectively increasing depth only for a small subset of parameters as training evolves. Extensive experiments across multiple parameter scales demonstrate that SGT consistently outperforms training-time static block-level looping baselines under comparable settings, while reducing the additional training FLOPs overhead from approximately 16--20% to only 1--3% relative to a standard Transformer backbone.

cs.CL↗

arXiv2026

Mixture of Universal Experts: Scaling Virtual Width via Depth-Width Transformation

Mixture-of-Experts (MoE) decouples model capacity from per-token computation, yet their scalability remains limited by the physical dimensions of depth and width. To overcome this, we propose Mixture of Universal Experts (MOUE),a MoE generalization introducing a novel scaling dimension: Virtual Width. In general, MoUE aims to reuse a universal layer-agnostic expert pool across layers, converting depth into virtual width under a fixed per-token activation budget. However, two challenges remain: a routing path explosion from recursive expert reuse, and a mismatch between the exposure induced by reuse and the conventional load-balancing objectives. We address these with three core components: a Staggered Rotational Topology for structured expert sharing, a Universal Expert Load Balance for depth-aware exposure correction, and a Universal Router with lightweight trajectory state for coherent multi-step routing. Empirically, MoUE consistently outperforms matched MoE baselines by up to 1.3% across scaling regimes, enables progressive conversion of existing MoE checkpoints with up to 4.2% gains, and reveals a new scaling dimension for MoE architectures.

cs.LG↗

arXiv2026

S2CDR: Smoothing-Sharpening Process Model for Cross-Domain Recommendation

User cold-start problem is a long-standing challenge in recommendation systems. Fortunately, cross-domain recommendation (CDR) has emerged as a highly effective remedy for the user cold-start challenge, with recently developed diffusion models (DMs) demonstrating exceptional performance. However, these DMs-based CDR methods focus on dealing with user-item interactions, overlooking correlations between items across the source and target domains. Meanwhile, the Gaussian noise added in the forward process of diffusion models would hurt user's personalized preference, leading to the difficulty in transferring user preference across domains. To this end, we propose a novel paradigm of Smoothing-Sharpening Process Model for CDR to cold-start users, termed as S2CDR which features a corruption-recovery architecture and is solved with respect to ordinary differential equations (ODEs). Specifically, the smoothing process gradually corrupts the original user-item/item-item interaction matrices derived from both domains into smoothed preference signals in a noise-free manner, and the sharpening process iteratively sharpens the preference signals to recover the unknown interactions for cold-start users. Wherein, for the smoothing process, we introduce the heat equation on the item-item similarity graph to better capture the correlations between items across domains, and further build the tailor-designed low-pass filter to filter out the high-frequency noise information for capturing user's intrinsic preference, in accordance with the graph signal processing (GSP) theory. Extensive experiments on three real-world CDR scenarios confirm that our S2CDR significantly outperforms previous SOTA methods in a training-free manner.

cs.IR↗

arXiv2026

From Agnostic to Specific: Latent Preference Diffusion for Multi-Behavior Sequential Recommendation

Multi-behavior sequential recommendation (MBSR) aims to learn the dynamic and heterogeneous interactions of users' multi-behavior sequences, so as to capture user preferences under target behavior for the next interacted item prediction. Unlike previous methods that adopt unidirectional modeling by mapping auxiliary behaviors to target behavior, recent concerns are shifting from behavior-fixed to behavior-specific recommendation. However, these methods still ignore the user's latent preference that underlying decision-making, leading to suboptimal solutions. Meanwhile, due to the asymmetric deterministic between items and behaviors, discriminative paradigm based on preference scoring is unsuitable to capture the uncertainty from low-entropy behaviors to high-entropy items, failing to provide efficient and diverse recommendation. To address these challenges, we propose \textbf{FatsMB}, a framework based diffusion model that guides preference generation \textit{\textbf{F}rom Behavior-\textbf{A}gnostic \textbf{T}o Behavior-\textbf{S}pecific} in latent spaces, enabling diverse and accurate \textit{\textbf{M}ulti-\textbf{B}ehavior Sequential Recommendation}. Specifically, we design a Multi-Behavior AutoEncoder (MBAE) to construct a unified user latent preference space, facilitating interaction and collaboration across Behaviors, within Behavior-aware RoPE (BaRoPE) employed for multiple information fusion. Subsequently, we conduct target behavior-specific preference transfer in the latent space, enriching with informative priors. A Multi-Condition Guided Layer Normalization (MCGLN) is introduced for the denoising. Extensive experiments on real-world datasets demonstrate the effectiveness of our model.

cs.IR↗

arXiv2026

SARM: LLM-Augmented Semantic Anchor for End-to-End Live-Streaming Ranking

Large-scale live-streaming recommendation requires precise modeling of non-stationary content semantics under strict real-time serving constraints. In industrial deployment, two common approaches exhibit fundamental limitations: discrete semantic abstractions sacrifice descriptive precision through clustering, while dense multimodal embeddings are extracted independently and remain weakly aligned with ranking optimization, limiting fine-grained content-aware ranking. To address these limitations, we propose \textbf{SARM}, an end-to-end ranking architecture that integrates natural-language semantic anchors directly into ranking optimization, enabling fine-grained author representations conditioned on multimodal content. Each semantic anchor is represented as learnable text tokens jointly optimized with ranking features, allowing the model to adapt content descriptions to ranking objectives. A lightweight dual-token gated design captures domain-specific live-streaming semantics, while an asymmetric deployment strategy preserves low-latency online training and serving. Extensive offline evaluation and large-scale A/B tests show consistent improvements over production baselines. SARM is fully deployed and serves over 400 million users daily.

cs.IR↗