Searcharxiv⌕ Search

arXiv subjects

Juntao Li

Publications and source records attributed to Juntao Li.

At least 37 records · Page 2Linked to original sources
arXiv2026

LongFlow: Efficient KV Cache Compression for Reasoning Models

Recent reasoning models such as OpenAI-o1 and DeepSeek-R1 have shown strong performance on complex tasks including mathematical reasoning and code generation. However, this performance gain comes with substantially longer output sequences, leading to significantly increased deployment costs. In particular, long outputs require large KV caches, resulting in high memory consumption and severe bandwidth pressure during attention computation. Most existing KV cache optimization methods are designed for long-input, short-output scenarios and are ineffective for the long-output setting of reasoning models. Moreover, importance estimation in prior work is computationally expensive and becomes prohibitive when continuous re-evaluation is required during long generation. To address these challenges, we propose LongFlow, a KV cache compression method with an efficient importance estimation metric derived from an intermediate result of attention computation using only the current query. This design introduces negligible computational overhead and requires no auxiliary storage. We further develop a custom kernel that fuses FlashAttention, importance estimation, and token eviction into a single optimized operator, improving system-level efficiency. Experiments show that LongFlow achieves up to an 11.8 times throughput improvement with 80% KV cache compression with minimal impact on model accuracy.

cs.LG↗
arXiv2026

ACT: Anti-Crosstalk Learning for Cross-Sectional Stock Ranking via Temporal Disentanglement and Structural Purification

Cross-sectional stock ranking is a fundamental task in quantitative investment, relying on both temporal modeling of individual stocks and the capture of inter-stock dependencies. While existing deep learning models leverage graph-based approaches to enhance ranking accuracy by propagating information over relational graphs, they suffer from a key challenge: crosstalk, namely unintended information interference across predictive factors. We identify two forms of crosstalk: temporal-scale crosstalk, where trends, fluctuations, and shocks are entangled in a shared representation and non-transferable local patterns contaminate cross-stock learning; and structural crosstalk, where heterogeneous relations are indiscriminately fused and relation-specific predictive signals are obscured. To address both issues, we propose the Anti-CrossTalk (ACT) framework for cross-sectional stock ranking via temporal disentanglement and structural purification. Specifically, ACT first decomposes each stock sequence into trend, fluctuation, and shock components, then extracts component-specific information through dedicated branches, which effectively decouples non-transferable local patterns. ACT further introduces a Progressive Structural Purification Encoder to sequentially purify structural crosstalk on the trend component after mitigating temporal-scale crosstalk. An adaptive fusion module finally integrates all branch representations for ranking. Experiments on CSI300 and CSI500 demonstrate that ACT achieves state-of-the-art ranking accuracy and superior portfolio performance, with improvements of up to 74.25% on the CSI300 dataset.

cs.LG↗
arXiv2026

When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math Reasoning

Large reasoning models (LRMs) have achieved strong performance enhancement through scaling test time computation, but due to the inherent limitations of the underlying language models, they still have shortcomings in tasks that require precise computation and extensive knowledge reserves. Tool-Integrated Reasoning (TIR) has emerged as a promising paradigm that incorporates tool call and execution within the reasoning trajectory. Although recent works have released some powerful open-source TIR models, our analysis reveals that these models still suffer from critical deficiencies. We find that when the reasoning of the model conflicts with the tool results, the model tends to believe in its own reasoning. And there are cases where the tool results are correct but are ignored by the model, resulting in incorrect answers, which we define as "Tool Ignored''. This indicates that the model does not know when to trust or ignore the tool. To overcome these limitations, We introduce Adaptive Tool Trust Calibration (ATTC), a novel framework that guides the model to adaptively choose to trust or ignore the tool results based on the confidence score of generated code blocks. The experimental results from various open-source TIR models of different sizes and across multiple datasets demonstrate that ATTC effectively reduces the "Tool Ignored" issue, resulting in a performance increase of 4.1% to 7.5%.

cs.CL↗
arXiv2026

When Is Thinking Enough? Early Exit via Sufficiency Assessment for Efficient Reasoning

Large reasoning models (LRMs) have achieved remarkable performance in complex reasoning tasks, driven by their powerful inference-time scaling capability. However, LRMs often suffer from overthinking, which results in substantial computational redundancy and significantly reduces efficiency. Early-exit methods aim to mitigate this issue by terminating reasoning once sufficient evidence has been generated, yet existing approaches mostly rely on handcrafted or empirical indicators that are unreliable and impractical. In this work, we introduce Dynamic Thought Sufficiency in Reasoning (DTSR), a novel framework for efficient reasoning that enables the model to dynamically assess the sufficiency of its chain-of-thought (CoT) and determine the optimal point for early exit. Inspired by human metacognition, DTSR operates in two stages: (1) Reflection Signal Monitoring, which identifies reflection signals as potential cues for early exit, and (2) Thought Sufficiency Check, which evaluates whether the current CoT is sufficient to derive the final answer. Experimental results on the Qwen3 models show that DTSR reduces reasoning length by 28.9%-34.9% with minimal performance loss, effectively mitigating overthinking. We further discuss overconfidence in LRMs and self-evaluation paradigms, providing valuable insights for early-exit reasoning.

cs.CL↗
arXiv2026

Where Matters More Than What: Decoding-aligned KV Cache Compression via Position-aware Pseudo Queries

The Key-Value (KV) cache is crucial for efficient Large Language Models (LLMs) inference, but excessively long contexts drastically increase KV cache memory footprint. Existing KV cache compression methods typically rely on input-side attention patterns within a prompt observation window to estimate token importance during the prefill stage. They fail to preserve critical tokens for future generation since these assessments are not derived from the decoding process. Intuitively, an effective observation window should mirror the decoding-stage queries to accurately reflect which tokens the generation process will attend to. However, ground-truth decoding queries are inherently unavailable during inference. For constructing pseudo queries to approximate them, we find that positional information plays a more critical role than semantic content. Motivated by this insight, we propose decoding-aligned KV cache compression via position-aware pseudo queries (DapQ), a novel and lightweight eviction framework that leverages position-aware pseudo queries to simulate the output tokens, thereby establishing an effective observation window for importance assessment. It aligns closely with the actual generation context and enables precise token eviction. Extensive evaluations across multiple benchmarks and LLMs demonstrate that DapQ achieves superior performance, particularly under strict memory constraints (e.g., up to nearly lossless performance 99.5% on NIAH with 3% KV cache budgets).

cs.CL↗
arXiv2026

$\textbf{Re}^{2}$: Unlocking LLM Reasoning via Reinforcement Learning with Re-solving

Reinforcement learning with verifiable rewards (RLVR) has shown promise in enhancing the reasoning performance of large language models (LLMs) by increasing test-time compute. However, even after extensive RLVR training, such models still tend to generate unnecessary and low-quality steps in their chain-of-thought (CoT), leading to inefficient overthinking and lower answer quality. We show that when the initial direction or quality of the CoT is suboptimal, the model often fails to reach the correct answer, even after generating several times more tokens than when the initial CoT is well-initialized. To this end, we introduce Reinforcement Learning with Re-solving (Re$^2$), in which LLMs learn to flexibly abandon unproductive reasoning paths and restart the solution process when necessary, rather than always committing to a final answer. Re$^2$ applies pure reinforcement learning without any preliminary supervised fine-tuning, successfully amplifying the rare redo behavior in vanilla models from only 0.5% to over 30%. This leads to substantial performance gains over standard RLVR under the same training compute budget, and also demonstrates notable improvements in test-time performance as the number of samples increases.

cs.AI↗
arXiv2026

FAPO: Flawed-Aware Policy Optimization for Efficient and Reliable Reasoning

Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising paradigm for enhancing the reasoning capabilities of large language models (LLMs). In this context, models explore reasoning trajectories and exploit rollouts with correct answers as positive signals for policy optimization. However, these rollouts might involve flawed patterns such as answer-guessing and jump-in-reasoning. Such flawed-positive rollouts are rewarded identically to fully correct ones, causing policy models to internalize these unreliable reasoning patterns. In this work, we first conduct a systematic study of flawed-positive rollouts in RL and find that they enable rapid capability gains during the early optimization stage, while constraining reasoning capability later by reinforcing unreliable patterns. Building on these insights, we propose Flawed-Aware Policy Optimization (FAPO), which presents a parameter-free reward penalty for flawed-positive rollouts, enabling the policy to leverage them as useful shortcuts in the warm-up stage, securing stable early gains, while gradually shifting optimization toward reliable reasoning in the later refinement stage. To accurately and comprehensively detect flawed-positive rollouts, we introduce a generative reward model (GenRM) with a process-level reward that precisely localizes reasoning errors. Experiments show that FAPO is effective in broad domains, improving outcome correctness, process reliability, and training stability without increasing the token budget.

cs.LG↗
arXiv2026

A Survey: Spatiotemporal Consistency in Video Generation

Video generation aims to produce temporally coherent sequences of visual frames, representing a pivotal advancement in Artificial Intelligence Generated Content (AIGC). Compared to static image generation, video generation poses unique challenges: it demands not only high-quality individual frames but also strong temporal coherence to ensure consistency throughout the spatiotemporal sequence. Although research addressing spatiotemporal consistency in video generation has increased in recent years, systematic reviews focusing on this core issue remain relatively scarce. To fill this gap, this paper views the video generation task as a sequential sampling process from a high-dimensional spatiotemporal distribution, and further discusses spatiotemporal consistency. We provide a systematic review of the latest advancements in the field. The content spans multiple dimensions including generation models, feature representations, generation frameworks, post-processing techniques, training strategies, benchmarks and evaluation metrics, with a particular focus on the mechanisms and effectiveness of various methods in maintaining spatiotemporal consistency. Finally, this paper explores future research directions and potential challenges in this field, aiming to provide valuable insights for advancing video generation technology. The project link is https://github.com/Yin-Z-Y/A-Survey-Spatiotemporal-Consistency-in-Video-Generation.

cs.CV↗
arXiv2026

Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers

The quadratic complexity of standard attention mechanisms poses a significant scalability bottleneck for large language models (LLMs) in long-context scenarios. While hybrid attention strategies that combine sparse and full attention within a single model offer a viable solution, they typically employ static computation ratios (i.e., fixed proportions of sparse versus full attention) and fail to adapt to the varying sparsity sensitivities of downstream tasks during inference. To address this issue, we propose Elastic Attention, which allows the model to dynamically adjust its overall sparsity based on the input. This is achieved by integrating a lightweight Attention Router into the existing pretrained model, which dynamically assigns each attention head to different computation modes. Within only 12 hours of training on 8xA800 GPUs, our method enables models to achieve both strong performance and efficient inference. Experiments across three long-context benchmarks on widely-used LLMs demonstrate the superiority of our method.

cs.CL↗
arXiv2026

MemoryRewardBench: Benchmarking Reward Models for Long-Term Memory Management in Large Language Models

Existing works increasingly adopt memory-centric mechanisms to process long contexts in a segment manner, and effective memory management is one of the key capabilities that enables large language models to effectively propagate information across the entire sequence. Therefore, leveraging reward models (RMs) to automatically and reliably evaluate memory quality is critical. In this work, we introduce MemoryRewardBench, the first benchmark to systematically study the ability of RMs to evaluate long-term memory management processes. MemoryRewardBench covers both long-context comprehension and long-form generation tasks, featuring 10 distinct settings with different memory management patterns, with context length ranging from 8K to 128K tokens. Evaluations on 13 cutting-edge RMs indicate a diminishing performance gap between open-source and proprietary models, with newer-generation models consistently outperforming their predecessors regardless of parameter count. We further expose the capabilities and fundamental limitations of current RMs in evaluating LLM memory management across diverse settings.

cs.CL↗
arXiv2025

Accelerate Speculative Decoding with Sparse Computation in Verification

Speculative decoding accelerates autoregressive language model inference by verifying multiple draft tokens in parallel. However, the verification stage often becomes the dominant computational bottleneck, especially for long-context inputs and mixture-of-experts (MoE) models. Existing sparsification methods are designed primarily for standard token-by-token autoregressive decoding to remove substantial computational redundancy in LLMs. This work systematically adopts different sparse methods on the verification stage of the speculative decoding and identifies structured redundancy across multiple dimensions. Based on these observations, we propose a sparse verification framework that jointly sparsifies attention, FFN, and MoE components during the verification stage to reduce the dominant computation cost. The framework further incorporates an inter-draft token and inter-layer retrieval reuse strategy to further reduce redundant computation without introducing additional training. Extensive experiments across summarization, question answering, and mathematical reasoning datasets demonstrate that the proposed methods achieve favorable efficiency-accuracy trade-offs, while maintaining stable acceptance length.

cs.CL↗
arXiv2025

Think Before You Prune: Selective Self-Generated Calibration for Pruning Large Reasoning Models

Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex reasoning benchmarks. However, their long chain-of-thought reasoning processes incur significant inference overhead. Pruning has emerged as a promising approach to reducing computational costs. However, existing efforts have primarily focused on large language models (LLMs), while pruning LRMs remains unexplored. In this work, we conduct the first empirical study on pruning LRMs and show that directly applying existing pruning techniques fails to yield satisfactory results. Our findings indicate that using self-generated reasoning data for calibration can substantially improve pruning performance. We further investigate how the difficulty and length of reasoning data affect pruning outcomes. Our analysis reveals that challenging and moderately long self-generated reasoning data serve as ideal calibration data. Based on these insights, we propose a Selective Self-Generated Reasoning (SSGR) data construction strategy to provide effective calibration data for pruning LRMs. Experimental results on the DeepSeek-R1-Distill model series validate that our strategy improves the reasoning ability of pruned LRMs by 10%-13% compared to general pruning methods.

cs.CL↗
arXiv2025

$A^3$: Attention-Aware Accurate KV Cache Fusion for Fast Large Language Model Serving

Large language models (LLMs) have demonstrated strong capabilities in processing long contexts, enabling them to tackle tasks involving long textual inputs such as multi-turn conversations, legal documents, or retrieved documents in Retrieval-Augmented Generation (RAG) systems. However, despite their ability to handle long sequences, the resulting decoding latency and memory overhead remain substantial, posing challenges for real-world deployment. Recent advances in KV Cache reuse have shown potential to mitigate these costs, but still suffer from notable performance degradation. To address this issue, we conduct an in-depth investigation of recomputation-based reuse methods and observe that the recomputed tokens often fail to align with the context segments most relevant to the question. This misalignment hinders proper updates to the critical contextual representations. Therefore, we propose the $\textbf{A}$ttention-$\textbf{A}$ware $\textbf{A}$ccurate KV Cache Fusion algorithm ($A^3$), which precomputes and selectively fuses the KV Cache of text chunks based on their relevance to the question, achieving accurate integration with minimal computational overhead. Extensive experiments on various benchmarks and LLMs demonstrate that $A^3$ achieves the best task performance compared to four baselines while reducing the time-to-first-token (TTFT) by 2$\times$.

cs.CL↗
arXiv2025

Overview of CHIP 2025 Shared Task 2: Discharge Medication Recommendation for Metabolic Diseases Based on Chinese Electronic Health Records

Discharge medication recommendation plays a critical role in ensuring treatment continuity, preventing readmission, and improving long-term management for patients with chronic metabolic diseases. This paper present an overview of the CHIP 2025 Shared Task 2 competition, which aimed to develop state-of-the-art approaches for automatically recommending appro-priate discharge medications using real-world Chinese EHR data. For this task, we constructed CDrugRed, a high-quality dataset consisting of 5,894 de-identified hospitalization records from 3,190 patients in China. This task is challenging due to multi-label nature of medication recommendation, het-erogeneous clinical text, and patient-specific variability in treatment plans. A total of 526 teams registered, with 167 and 95 teams submitting valid results to the Phase A and Phase B leaderboards, respectively. The top-performing team achieved the highest overall performance on the final test set, with a Jaccard score of 0.5102, F1 score of 0.6267, demonstrating the potential of advanced large language model (LLM)-based ensemble systems. These re-sults highlight both the promise and remaining challenges of applying LLMs to medication recommendation in Chinese EHRs. The post-evaluation phase remains open at https://tianchi.aliyun.com/competition/entrance/532411/.

cs.CL↗
arXiv2025

Revisiting Long-context Modeling from Context Denoising Perspective

Long-context models (LCMs) have demonstrated great potential in processing long sequences, facilitating many real-world applications. The success of LCMs can be attributed to their ability to locate implicit critical information within the context for further prediction. However, recent research reveals that LCMs are often susceptible to contextual noise, i.e., irrelevant tokens, that can mislead model attention. In this paper, we conduct a fine-grained analysis of the context noise and propose an effective metric, the Integrated Gradient (IG) score, to detect and quantify the noise information within the context. Our findings reveal that even simple mitigation of detected context noise can substantially boost the model's attention on critical tokens and benefit subsequent predictions. Building on this insight, we propose Context Denoising Training (CDT), a straightforward yet effective training strategy that improves attention on critical tokens while reinforcing their influence on model predictions. Extensive experiments across four tasks, under both context window scaling and long-context alignment settings, demonstrate the superiority of CDT. Notably, when trained with CDT, an open-source 8B model can achieve performance (50.92) comparable to GPT-4o (51.00).

cs.CL↗
arXiv2025

LongRM: Revealing and Unlocking the Context Boundary of Reward Modeling

Reward model (RM) plays a pivotal role in aligning large language model (LLM) with human preferences. As real-world applications increasingly involve long history trajectories, e.g., LLM agent, it becomes indispensable to evaluate whether a model's responses are not only high-quality but also grounded in and consistent with the provided context. Yet, current RMs remain confined to short-context settings and primarily focus on response-level attributes (e.g., safety or helpfulness), while largely neglecting the critical dimension of long context-response consistency. In this work, we introduce Long-RewardBench, a benchmark specifically designed for long-context RM evaluation, featuring both Pairwise Comparison and Best-of-N tasks. Our preliminary study reveals that even state-of-the-art generative RMs exhibit significant fragility in long-context scenarios, failing to maintain context-aware preference judgments. Motivated by the analysis of failure patterns observed in model outputs, we propose a general multi-stage training strategy that effectively scales arbitrary models into robust Long-context RMs (LongRMs). Experiments show that our approach not only substantially improves performance on long-context evaluation but also preserves strong short-context capability. Notably, our 8B LongRM outperforms much larger 70B-scale baselines and matches the performance of the proprietary Gemini 2.5 Pro model.

cs.CL↗
arXiv2025

XIFBench: Evaluating Large Language Models on Multilingual Instruction Following

Large Language Models (LLMs) have demonstrated remarkable instruction-following capabilities across various applications. However, their performance in multilingual settings lacks systematic investigation, with existing evaluations lacking fine-grained constraint analysis across diverse linguistic contexts. We introduce XIFBench, a comprehensive constraint-based benchmark for evaluating multilingual instruction-following abilities of LLMs, comprising 558 instructions with 0-5 additional constraints across five categories (Content, Style, Situation, Format, and Numerical) in six languages spanning different resource levels. To support reliable and consistent cross-lingual evaluation, we implement three methodological innovations: cultural accessibility annotation, constraint-level translation validation, and requirement-based evaluation using English requirements as semantic anchors across languages. Extensive experiments with various LLMs not only quantify performance disparities across resource levels but also provide detailed insights into how language resources, constraint categories, instruction complexity, and cultural specificity influence multilingual instruction-following. Our code and data are available at https://github.com/zhenyuli801/XIFBench.

cs.CL↗
arXiv2025

SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning

Process reward models (PRMs) offer fine-grained, step-level evaluations that facilitate deeper reasoning processes in large language models (LLMs), proving effective in complex tasks like mathematical reasoning. However, developing PRMs is challenging due to the high cost and limited scalability of human-annotated data. Synthetic data from Monte Carlo (MC) estimation is a promising alternative but suffers from a high noise ratio, which can cause overfitting and hinder large-scale training. In this work, we conduct a preliminary study on the noise distribution in synthetic data from MC estimation, identifying that annotation models tend to both underestimate and overestimate step correctness due to limitations in their annotation capabilities. Building on these insights, we propose Self-Denoising Monte Carlo Annotation (SCAN), an efficient data synthesis and noise-tolerant learning framework. Our key findings indicate that: (1) Even lightweight models (e.g., 1.5B parameters) can produce high-quality annotations through a self-denoising strategy, enabling PRMs to achieve superior performance with only 6% the inference cost required by vanilla MC estimation. (2) With our robust learning strategy, PRMs can effectively learn from this weak supervision, achieving a 39.2 F1 score improvement (from 19.9 to 59.1) in ProcessBench. Despite using only a compact synthetic dataset, our models surpass strong baselines, including those trained on large-scale human-annotated datasets such as PRM800K. Furthermore, performance continues to improve as we scale up the synthetic data, highlighting the potential of SCAN for scalable, cost-efficient, and robust PRM training.

cs.LG↗