arXiv subjects

Tongxuan Liu

Publications and source records attributed to Tongxuan Liu.

At least 19 recordsLinked to original sources

arXiv2026

HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention

Token-level sparse attention mechanisms, exemplified by DeepSeek Sparse Attention (DSA), achieve fine-grained key selection by scoring every historical key for each query through a lightweight indexer, then computing attention only on the selected subset. While the downstream sparse attention itself scales favorably, the indexer must still scan the entire prefix for every query, introducing an per-layer bottleneck that grows prohibitively with context length. We propose HISA (Hierarchical Indexed Sparse Attention), a plug-and-play replacement for the indexer that rewrites the search path from a flat token scan into a two-stage hierarchical procedure: (1) a block-level coarse filtering stage that scores pooled block representations to discard irrelevant regions, followed by (2) a token-level refinement stage that applies the original indexer exclusively within the retained candidate blocks. HISA preserves the identical token-level top-sparse pattern consumed by the downstream Sparse MLA operator and requires no additional training. On kernel-level benchmarks, HISA achieves up to speedup at 64K context. On Needle-in-a-Haystack and LongBench, we directly replace the indexer in DeepSeek-V3.2 and GLM-5 with our HISA indexer, without any finetuning. HISA closely matches the original DSA in quality, while substantially outperforming block-sparse baselines.

cs.LG↗

arXiv2026

PosterText: Towards Unified Visual Text Generation and Editing for E-commerce Poster

Automated e-commerce poster design requires both high-quality poster generation and flexible editing of existing designs. However, most existing methods either target end-to-end poster generation or follow multi-stage design pipelines, with limited capability for flexible and precise editing of existing posters. To enable unified generation and editing of e-commerce posters, we introduce Text Patch Generation and Editing, a unified task formulation that treats text patches as atomic units and covers four operations: poster generation, patch addition, patch deletion, and patch modification, with optional reference-guided style control. Based on this, we propose PosterText, a unified model trained with a four-stage curriculum, including text rendering pretraining, instruction-following training, reinforcement learning for preference alignment, and spatial guidance self-distillation for execution refinement. We further construct a large-scale dataset with patch-level annotations and a comprehensive benchmark for evaluation. Extensive experiments demonstrate that PosterText achieves competitive performance against existing generation and editing approaches, validating the effectiveness of the proposed framework.

cs.CV↗

arXiv2026

iFAN: Inference-Aware Learning for Plain Mask Transformers

Query-based mask transformers assemble segmentation outputs through pixel-wise competition among query predictions of the final layer, yet this inference process is not explicitly optimized during training. We identify two key mismatches: the query with the highest probability-mask score does not necessarily produce the most accurate mask, and final-layer decoding may discard superior predictions from intermediate layers. To address these issues, we propose Inference-Aware Learning (iFAN), a general training framework for plain mask transformers. iFAN introduces Adjusted Probability-Mask Ranking (APMR), which aligns query competition with predicted mask quality and suppresses high-confidence but inaccurate competitors. We further employ Cross-Layer Self-Distillation (CLSD) to transfer stronger intermediate predictions to the final layer. The ranking and distillation objectives are training-only, while inference retains efficient final-layer decoding. Experiments on COCO, ADE20K, and Cityscapes demonstrate consistent improvements across panoptic, instance, and semantic segmentation, as well as across different architectures, backbone scales, and input resolutions. Overall, iFAN improves performance by an average of 1.20 PQ, 1.30 AP, and 0.63 mIoU, with negligible additional parameters, FLOPs and inference latency.

cs.CV↗

arXiv2026

xGR: Efficient Generative Recommendation Serving at Scale

Recommendation system delivers substantial economic benefits by providing personalized predictions. Generative recommendation (GR) integrates LLMs to enhance the understanding of long user-item sequences. Despite employing attention-based architectures, GR's workload differs markedly from that of LLM serving. GR typically processes long prompt while producing short, fixed-length outputs, yet the computational cost of each decode phase is especially high due to the large beam width. Furthermore, since the beam search involves a vast item space, the sorting overhead becomes particularly time-consuming. We propose xGR, a GR-oriented serving system that meets strict low-latency requirements under high-concurrency scenarios. First, xGR unifies the processing of prefill and decode phases through staged computation and separated KV cache. Second, xGR enables early sorting termination and mask-based item filtering with data structure reuse. Third, xGR reconstructs the overall pipeline to exploit multi-level overlap and multi-stream parallelism. The experiments on real-world datasets demonstrate that xGR achieves at least 2.89x throughput compared to the state-of-the-art baseline under strict latency constraints.

cs.LG↗

arXiv2026

BLADE: Scalable Bi-level Adaptive Data Selection for LLM Training

As Large Language Model (LLM) datasets scale to trillions of tokens, data selection has emerged as a critical frontier to filter out uninformative noise and construct adaptive learning trajectories. Beyond static heuristic filtering, advanced data selection methods for LLM training largely follow two paradigms, each with fundamental limitations. Influence-based methods provide principled bi-level objectives but require intractable inverse-Hessian computations, while excess-loss methods are computationally efficient but rely on a static reference model that becomes misaligned with the evolving proxy model during training. We propose BLADE (Bi-Level Adaptive Data sElection), a Hessian-free framework for data selection. BLADE reformulates the bi-level optimization problem underlying influence-based methods as a penalized single-level objective via Lagrange multipliers, avoiding inverse-Hessian computation while revealing a principled connection to excess-loss based data selection. The resulting objective recovers an excess-loss form but replaces the static reference model with a dynamic one that stays synchronized with training. Theoretically, we prove that this penalized formulation guarantees first-order convergence. For efficient online batch selection, we instantiate BLADE as a memoryless randomized block-coordinate Frank-Wolfe algorithm. Extensive experiments show that BLADE consistently outperforms state-of-the-art data selection baselines, providing a practical recipe for LLM training.

cs.LG↗

arXiv2026

ProServe: Unified Multi-Priority Request Scheduling for LLM Serving

The widespread deployment of large language models (LLMs) for interactive applications necessitates serving systems that can handle thousands of concurrent requests with diverse Service Level Objective (SLO) requirements. A critical yet often overlooked dimension in this context is the inherent priority difference among clients; for instance, business-critical functions demand higher performance guarantees, as fulfilling such requests yields significantly greater business value. However, existing LLM serving schedulers fail to jointly optimize for both SLO attainment and client-level priorities. To bridge this gap, we first formalize multi-priority request scheduling as a service gain maximization problem, where satisfying latency requirements for requests of different priorities contributes varying gain. We propose ProServe, a unified two-tier scheduling framework designed to maximize overall service gain. At the engine layer, SlideBatching dynamically adapts batch formation under varying loads, employing a sliding boundary mechanism to balance latency and priority differentiation. Considering potential preemption, efficient block management adopts asynchronous offloading, pipelined reloading, and adaptive copy-budget control to overlap computation with host-device block transfers. At the service layer, GoRouting performs gain-oriented and capability-aware dispatching across distributed instances, proactively reserving capacity for future high-priority or long requests. Extensive evaluation on four open-source and one industrial dataset shows that ProServe outperforms state-of-the-art baselines, improving system gain by up to 35% and SLO attainment by up to 52%.

cs.DC↗

arXiv2026

RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference

DeepSeek-OCR leverages visual-text compression to reduce long-text processing costs and accelerate inference, yet visual tokens remain prone to redundant textual and structural information. Moreover, current token pruning methods for conventional vision-language models (VLMs) fail to preserve textual fidelity due to improper compression mechanisms. By analyzing the decoding process of DeepSeek-OCR, we find that a distinct two-stage reading trajectory: the model initially prioritizes the majority of high-norm tokens, then subsequently redistributes its attention to the remaining ones. Motivated by this insight, we propose RTPrune, a two-stage token pruning method tailored for DeepSeek-OCR. In the first stage, we prioritize high-norm visual tokens that capture salient textual and structural information. In the second stage, the remaining tokens are paired and merged based on optimal transport theory to achieve efficient feature aggregation. We further introduce a dynamic pruning ratio that adapts to token similarity and textual density for OCR tasks, enabling a better efficiency-accuracy trade-off. Extensive experiments demonstrate state-of-the-art performance, as evidenced by 99.47% accuracy and 1.23$\times$ faster prefill on OmniDocBench, achieved with 84.25% token retention when applied to DeepSeek-OCR-Large.

cs.CV↗

arXiv2026

FastOCR: Dynamic Visual Fixation via KV Cache Pruning for Efficient Document Parsing

Vision-Language Models (VLMs) have shown strong promise on Optical Character Recognition (OCR), yet the sheer number of visual tokens required to encode dense documents incurs prohibitive inference cost. Existing pruning methods rely on physical eviction, e.g., permanently discarding visual tokens during the prefill stage. While effective for natural images, this strategy fundamentally breaks down on OCR, where virtually every visual token may correspond to a character or structural element, and any irreversible loss leads to catastrophic accuracy degradation. We observe that, although document images appear globally dense and seemingly unprunable, the model's attention to them is in fact temporally sparse: at each decoding step it concentrates on a small region that shifts gradually across steps, much as a human reader fixates on successive words rather than perceiving an entire page at once. Motivated by this Dynamic Visual Fixation phenomenon, we recast the intractable global pruning problem as a tractable local, dynamic one and propose FastOCR, a training-free framework with two complementary modules. Specifically, Focal-Guided Pruning identifies a small set of focal layers and selects the most task-relevant visual tokens from them at each step, while Cross-Step Fixation Reuse exploits the gradual shift of fixation to warm-start each step from the previous one. By dynamically adjusting which tokens are attended rather than evicting any from the cache, FastOCR avoids permanent information loss. Extensive experiments show that FastOCR serves as a plug-and-play acceleration module, generalizing consistently across five VLMs of varying sizes and architectures. On Qwen2.5-VL, FastOCR retains 98% of the unpruned model's accuracy while attending to only 5% of the visual tokens per decoding step, reducing attention latency by 3.0$\times$.

cs.CV↗

arXiv2026

MISA: Mixture of Indexer Sparse Attention for Long-Context LLM Inference

DeepSeek Sparse Attention (DSA) sets the state of the art for fine-grained inference-time sparse attention by introducing a learned token-wise indexer that scores every prefix token and selects the most relevant ones for the main attention. To remain expressive, the indexer uses many query heads (for example, 64 on DeepSeek-V3.2) that share the same selected token set; this multi-head design is precisely what makes the indexer the dominant cost on long contexts. We propose MISA (Mixture of Indexer Sparse Attention), a drop-in replacement for the DSA indexer that treats its indexer heads as a pool of mixture-of-experts. A lightweight router uses cheap block-level statistics to pick a query-dependent subset of only a few active heads, and only those heads run the heavy token-level scoring. This preserves the diversity of the original indexer pool while reducing the per-query cost from scoring every prefix token with every head to scoring it with only a handful of routed heads, plus a negligible router term computed on a small set of pooled keys. We further introduce a hierarchical variant of MISA that uses the routed pass to keep an enlarged candidate set and then re-ranks it with the original DSA indexer to recover the final selected tokens almost exactly. With only eight active heads and no additional training, MISA matches the dense DSA indexer on LongBench across DeepSeek-V3.2 and GLM-5 while running with eight and four times fewer indexer heads respectively, and outperforms HISA on average. It also preserves fully green Needle-in-a-Haystack heatmaps up to a 128K-token context and recovers more than 92% of the tokens selected by the DSA indexer per layer. Our TileLang kernel delivers roughly a 3.82 times speedup over DSA's original indexer kernel on a single NVIDIA H200 GPU.

cs.LG↗

arXiv2026

TARAC: Mitigating Hallucination in LVLMs via Temporal Attention Real-time Accumulative Connection

Large Vision-Language Models have demonstrated remarkable capabilities, yet they suffer from hallucinations that limit practical deployment. While various mitigation strategies exist, they often incur high computational overhead or require extensive retraining. In this paper, we address the issue of visual attention decay during generation, a key factor contributing to hallucinations. We propose Temporal Attention Real-time Accumulative Connection (TARAC), a novel training-free framework that dynamically accumulates and re-injects historical attention to sustain visual grounding. Inspired by cognitive reinforcement mechanisms, TARAC operates as a lightweight, plug-and-play module. Extensive experiments across diverse models (e.g., LLaVA, Qwen2-VL) and benchmarks demonstrate that TARAC significantly outperforms state-of-the-art methods. Remarkably, it achieves these gains with negligible inference overhead ($\sim$4\% TPOT increase), compared to the substantial costs of existing training-free baselines. Specifically, TARAC reduces hallucinated sentences by 25.2\% on CHAIR and improves Perception score by +10.65 on MME, validating its effectiveness and efficiency.

cs.CV↗

arXiv2026

xLLM Technical Report

We introduce xLLM, an intelligent and efficient Large Language Model (LLM) inference framework designed for high-performance, large-scale enterprise-grade serving, with deep optimizations for diverse AI accelerators. To address these challenges, xLLM builds a novel decoupled service-engine architecture. At the service layer, xLLM-Service features an intelligent scheduling module that efficiently processes multimodal requests and co-locates online and offline tasks through unified elastic scheduling to maximize cluster utilization. This module also relies on a workload-adaptive dynamic Prefill-Decode (PD) disaggregation policy and a novel Encode-Prefill-Decode (EPD) disaggregation policy designed for multimodal inputs. Furthermore, it incorporates a distributed architecture to provide global KV Cache management and robust fault-tolerant capabilities for high availability. At the engine layer, xLLM-Engine co-optimizes system and algorithm designs to fully saturate computing resources. This is achieved through comprehensive multi-layer execution pipeline optimizations, an adaptive graph mode and an xTensor memory management. xLLM-Engine also further integrates algorithmic enhancements such as optimized speculative decoding and dynamic EPLB, collectively serving to substantially boost throughput and inference efficiency. Extensive evaluations demonstrate that xLLM delivers significantly superior performance and resource efficiency. Under identical TPOT constraints, xLLM achieves throughput up to 1.7x that of MindIE and 2.2x that of vLLM-Ascend with Qwen-series models, while maintaining an average throughput of 1.7x that of MindIE with Deepseek-series models. xLLM framework is publicly available at https://github.com/jd-opensource/xllm and https://github.com/jd-opensource/xllm-service.

cs.DC↗

arXiv2026

Are LLMs Stable Formal Logic Translators in Logical Reasoning Across Linguistically Diversified Texts?

Logical reasoning with large language models (LLMs) has received growing attention. One mainstream approach translates natural language into formal logic and then applies symbolic solvers for deduction. While effective in many tasks, these LLM-based translators often fail to generate consistent symbolic representations when the same concept appears in different linguistic forms. Such inconsistencies break logical coherence and lead to solver errors. However, most existing benchmarks lack this type of linguistic variation, which frequently occurs in real-world text, leaving the problem underexplored. To address this gap, we present SoLT, a benchmark that systematically rewrites reasoning datasets into diverse yet logically equivalent forms across multiple levels. Beyond evaluation, SoLT also provides a general method to enrich any dataset with linguistic diversity while preserving both meaning and logic. To further enhance the stability of LLM-based reasoning, we propose MenTaL, which explicitly guides models to build a concept-symbol mapping table during translation. By linking equivalent expressions to shared symbols, MenTaL maintains consistency and mitigates symbol drift. Experiments on SoLT demonstrate that LLMs indeed suffer from inconsistent symbol mapping under linguistic variation, leading to significant drops in reasoning accuracy. Meanwhile, applying MenTaL brings clear and stable performance improvements across diverse inputs. Overall, our findings reveal that overlooking linguistic diversity hides key weaknesses in LLM-based translators, and our work offers a step toward more reliable logical reasoning in varied real-world scenarios. Our code is available at https://github.com/wufeiwuwoshihua/LinguDiver.

cs.CL↗

arXiv2026

Do Transformers Have the Ability for Periodicity Generalization?

Large language models (LLMs) based on the Transformer have demonstrated strong performance across diverse tasks. However, current models still exhibit substantial limitations in out-of-distribution (OOD) generalization compared with humans. We investigate this gap through periodicity, one of the basic OOD scenarios. Periodicity captures invariance amid variation. Periodicity generalization represents a model's ability to extract periodic patterns from training data and generalize to OOD scenarios. We introduce a unified interpretation of periodicity from the perspective of abstract algebra and reasoning, including both single and composite periodicity, to explain why Transformers struggle to generalize periodicity. Then we construct Coper about composite periodicity, a controllable generative benchmark with two OOD settings, Hollow and Extrapolation. Experiments reveal that periodicity generalization in Transformers is limited, where models can memorize periodic data during training, but cannot generalize to unseen composite periodicity. We release the source code to support future research.

cs.LG↗

arXiv2026

IFDNS: An Iterative Feedback-Driven Neuro-Symbolic Method for Faithful Logical Reasoning

Large language models (LLMs) have demonstrated impressive capabilities across a wide range of reasoning tasks, including logical and mathematical problem-solving. While prompt-based methods like Chain-of-Thought (CoT) can enhance LLM reasoning abilities to some extent, they often suffer from a lack of faithfulness, where the derived conclusions may not align with the generated reasoning chain. To address this issue, researchers have explored neuro-symbolic approaches to bolster LLM logical reasoning capabilities. However, existing neuro-symbolic methods still face challenges with information loss during the process. To overcome these limitations, we introduce Iterative Feedback-Driven Neuro-Symbolic (IFDNS), a novel prompt-based method that employs a multi-round feedback mechanism to address LLM limitations in handling complex logical relationships. IFDNS utilizes iterative feedback during the logic extraction phase to accurately extract causal relationship statements and translate them into propositional and logical implication expressions, effectively mitigating information loss issues. Furthermore, IFDNS is orthogonal to existing prompt methods, allowing for seamless integration with various prompting approaches. Empirical evaluations across six datasets demonstrate the effectiveness of IFDNS in significantly improving the performance of CoT and Chain-of-Thought with Self-Consistency (CoT-SC). Specifically, IFDNS achieves a +9.40% accuracy boost for CoT on the LogiQA dataset and a +11.70% improvement for CoT-SC on the PrOntoQA dataset.

cs.AI↗

arXiv2025

OxygenREC: An Instruction-Following Generative Framework for E-commerce Recommendation

Traditional recommendation systems suffer from inconsistency in multi-stage optimization objectives. Generative Recommendation (GR) mitigates them through an end-to-end framework; however, existing methods still rely on matching mechanisms based on inductive patterns. Although responsive, they lack the ability to uncover complex user intents that require deductive reasoning based on world knowledge. Meanwhile, LLMs show strong deep reasoning capabilities, but their latency and computational costs remain challenging for industrial applications. More critically, there are performance bottlenecks in multi-scenario scalability: as shown in Figure 1, existing solutions require independent training and deployment for each scenario, leading to low resource utilization and high maintenance costs-a challenge unaddressed in GR literature. To address these, we present OxygenREC, an industrial recommendation system that leverages Fast-Slow Thinking to deliver deep reasoning with strict latency and multi-scenario requirements of real-world environments. First, we adopt a Fast-Slow Thinking architecture. Slow thinking uses a near-line LLM pipeline to synthesize Contextual Reasoning Instructions, while fast thinking employs a high-efficiency encoder-decoder backbone for real-time generation. Second, to ensure reasoning instructions effectively enhance recommendation generation, we introduce a semantic alignment mechanism with Instruction-Guided Retrieval (IGR) to filter intent-relevant historical behaviors and use a Query-to-Item (Q2I) loss for instruction-item consistency. Finally, to resolve multi-scenario scalability, we transform scenario information into controllable instructions, using unified reward mapping and Soft Adaptive Group Clip Policy Optimization (SA-GCPO) to align policies with diverse business objectives, realizing a train-once-deploy-everywhere paradigm.

cs.IR↗

arXiv2025

GroupDebate: Enhancing the Efficiency of Multi-Agent Debate Using Group Discussion

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse NLP tasks. Extensive research has explored how to enhance the logical reasoning abilities such as Chain-of-Thought, Chain-of-Thought with Self-Consistency, Tree-Of-Thoughts, and multi-agent debates. In the context of multi-agent debates, significant performance improvements can be achieved with an increasing number of agents and debate rounds. However, the escalation in the number of agents and debate rounds can drastically raise the tokens cost of debates, thereby limiting the scalability of the multi-agent debate technique. To better harness the advantages of multi-agent debates in logical reasoning tasks, this paper proposes a method to significantly reduce token cost in multi-agent debates. This approach involves dividing all agents into multiple debate groups, with agents engaging in debates within their respective groups and sharing interim debate results between groups. Comparative experiments across multiple datasets have demonstrated that this method can reduce the total tokens by up to 51.7% during debates and while potentially enhancing accuracy by as much as 25%. Our method significantly enhances the performance and efficiency of interactions in the multi-agent debate.

cs.CL↗

arXiv2025

From Hypothesis to Premises: LLM-based Backward Logical Reasoning with Selective Symbolic Translation

Logical reasoning is a core challenge in natural language understanding and a fundamental capability of artificial intelligence, underpinning scientific discovery, mathematical theorem proving, and complex decision-making. Despite the remarkable progress of large language models (LLMs), most current approaches still rely on forward reasoning paradigms, generating step-by-step rationales from premises to conclusions. However, such methods often suffer from redundant inference paths, hallucinated steps, and semantic drift, resulting in inefficient and unreliable reasoning. In this paper, we propose a novel framework, Hypothesis-driven Backward Logical Reasoning (HBLR). The core idea is to integrate confidence-aware symbolic translation with hypothesis-driven backward reasoning. In the translation phase, only high-confidence spans are converted into logical form, such as First-Order Logic (FOL), while uncertain content remains in natural language. A translation reflection module further ensures semantic fidelity by evaluating symbolic outputs and reverting lossy ones back to text when necessary. In the reasoning phase, HBLR simulates human deductive thinking by assuming the conclusion is true and recursively verifying its premises. A reasoning reflection module further identifies and corrects flawed inference steps, enhancing logical coherence. Extensive experiments on five reasoning benchmarks demonstrate that HBLR consistently outperforms strong baselines in both accuracy and efficiency.

cs.CL↗

arXiv2025

OOCO: Latency-disaggregated Architecture for Online-Offline Co-locate LLM Serving

Large Language Models (LLMs) are increasingly deployed in both latency-sensitive online services and cost-sensitive offline workloads. Co-locating these workloads on shared serving instances can improve resource utilization, but directly applying this approach to Prefill/Decode (P/D) disaggregated systems introduces severe load imbalance, as fluctuating request mixes alter the intrinsic P/D ratio. Existing dynamic adjustment techniques cannot keep up with the bursty traffic patterns of online services. We propose a latency-constraint disaggregated architecture, which separates cluster resources into latency-strict and latency-relaxed pools based on task latency requirements. This design enables flexible placement of offline decode tasks, mitigating P/D imbalance while preserving online performance. To fully exploit this flexibility, we propose (1) a bottleneck-based scheduler guided by a Roofline-based performance model for performance bottleneck based scheduling, and (2) a fast preemption mechanism that strictly enforces Service Level Objectives (SLOs) for online requests. Experiments on real-world traces show that compared to existing offline system approaches, our method improves offline throughput by up to 3x, while maintaining online request SLOs.

cs.DC↗