arXiv subjects

Qiang Liu

Publications and source records attributed to Qiang Liu.

At least 55 records · Page 3Linked to original sources

arXiv2026

KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answering

Knowledge Base Question Answering (KBQA) challenges models to bridge the gap between natural language and strict knowledge graph schemas by generating executable logical forms. While Large Language Models (LLMs) have advanced this field, current approaches often struggle with a dichotomy of failure: they either generate hallucinated queries without verifying schema existence or exhibit rigid, template-based reasoning that mimics synthesized traces without true comprehension of the environment. To address these limitations, we present \textbf{KBQA-R1}, a framework that shifts the paradigm from text imitation to interaction optimization via Reinforcement Learning. Treating KBQA as a multi-turn decision process, our model learns to navigate the knowledge base using a list of actions, leveraging Group Relative Policy Optimization (GRPO) to refine its strategies based on concrete execution feedback rather than static supervision. Furthermore, we introduce \textbf{Referenced Rejection Sampling (RRS)}, a data synthesis method that resolves cold-start challenges by strictly aligning reasoning traces with ground-truth action sequences. Extensive experiments on WebQSP, GrailQA, and GraphQuestions demonstrate that KBQA-R1 achieves state-of-the-art performance, effectively grounding LLM reasoning in verifiable execution.

cs.CL↗

arXiv2026

LOLLA: Deep Reinforcement Learning for Closed-Loop Link Adaptation Towards a GPU-Accelerated AI-RAN

Outer-loop link adaptation (OLLA) is widely deployed in 5G NR to track channel variations, yet its reliance on first-order, single-bit feedback degrades performance significantly under high-mobility and fast-varying channels. This paper presents LOLLA (Learned Outer-Loop Link Adaptation), a deep reinforcement learning framework that replaces the conventional OLLA staircase with a learned, continuous SINR offset conditioned on rich PHY/MAC telemetry inaccessible to OLLA. The offset modulates the SINR-to-MCS lookup table, preserving 3GPP-compliant MCS selection and provably subsuming the conventional OLLA update rule. A Proximal Policy Optimization (PPO) policy trained under a Lagrangian block error rate (BLER) constraint automatically enforces tunable reliability targets from 1% to 15% without manual penalty calibration. The framework is realized as the first closed-loop AI-native control dApp on a GPU-accelerated 5G NR stack, achieving end-to-end control latencies under 500 microseconds. Evaluations under 3GPP TDL channel models demonstrate 15% to 92% throughput gains over OLLA across Doppler frequencies up to 400 Hz, while attaining a Pareto frontier that strictly dominates OLLA across all evaluated reliability targets. The learned policy generalizes to unseen channel models and scales to eight concurrent UEs under shared-resource scheduling. In the uplink formulation, the gNB directly observes decoding outcomes, enabling simulation-to-deployment parity.

eess.SP↗

arXiv2026

CapRiCorn-1K: A Comprehensive Benchmark for Video Captioning and Subject Referential Consistency Across Temporal Scales

Accurate and comprehensive video captions with consistent subject references are critical for downstream understanding and generation tasks. However, few existing benchmarks can objectively and comprehensively evaluate these properties across diverse durations and scenarios, thereby hindering the advancement of video captioning models. To bridge this gap, we propose CapRiCorn-1K, a comprehensive benchmark designed to evaluate both video captioning quality and subject referential consistency across long temporal horizons and diverse video domains. To accommodate varied evaluation needs, our benchmark supports both audiovisual and visual-only settings. Extensive experiments on CapRiCorn-1K reveal that current models generally struggle to generate accurate and comprehensive captions while maintaining consistent subject references. Moreover, as video duration increases, both the overall caption quality and subject referential consistency decline. Notably, our evaluation metrics exhibit strong correlations with the performance of downstream understanding and generation tasks conditioned on the generated captions, further validating their effectiveness. The project is available at https://github.com/xlchen0205/CapRiCorn-1K .

cs.CV↗

arXiv2026

Non-line-of-sight imaging with arbitrary relay surface geometries via 3D Gaussian Transient Rendering

Imaging objects hidden outside the direct line of sight expands the effective field of view and is critical for applications such as autonomous driving and robotic perception. Despite impressive progress in time-of-flight (ToF)-based non-line-of-sight (NLOS) imaging, real-world deployment remains challenging because practical measurements are often collected over spatially limited, arbitrarily shaped relay regions-conditions that violate the planar-wall and dense-sampling assumptions made by most existing methods. To address these limitations, we propose a LOS-guided NLOS imaging pipeline that imposes no geometric assumptions on the relay surface and naturally supports both confocal and non-confocal configurations. Our method represents the hidden scene using 3D Gaussian primitives and couples them with an efficient, differentiable transient rendering model, enabling end-to-end optimization directly from measured transients. We validate our approach on real-world measurements from both a public dataset and a custom-built capture system. Across settings, our method achieves state-of-the-art reconstruction fidelity under spatially limited, sparsely sampled conditions, and significantly outperforms existing methods on complex, arbitrary relay surface geometries.

physics.optics↗

arXiv2026

RoboSSM: Scalable In-context Imitation Learning via State-Space Models

In-context imitation learning (ICIL) enables robots to learn tasks from prompts consisting of just a handful of demonstrations. By eliminating the need for parameter updates at deployment time, this paradigm supports few-shot adaptation to novel tasks. However, recent ICIL methods rely on Transformers, which have computational limitations and tend to underperform when handling longer prompts than those seen during training. In this work, we introduce RoboSSM, a scalable recipe for in-context imitation learning based on state-space models (SSM). Specifically, RoboSSM replaces Transformers with Longhorn -- a state-of-the-art SSM that provides linear-time inference and strong extrapolation capabilities, making it well-suited for long-context prompts. Through diverse experiments on the LIBERO benchmark, we demonstrate the effectiveness of applying SSMs to ICIL, achieving improved generalization to both unseen and long-horizon tasks than Transformer-based ICIL methods by handling longer contexts at test-time. These results show for the first time that SSMs are an efficient and scalable backbone for ICIL. Our code is available at https://github.com/youngjuY/RoboSSM.

cs.RO↗

arXiv2026

SoK: Taxonomizing the Low-Level Attack Surface of Modern Web Browsers

The web browser remains one of the most exposed remote attack surfaces on end-user systems, and memory-corruption flaws continue to play a central role in real-world browser exploitation. Despite a decade of intensive browser testing and bug-disclosure efforts, the community still lacks an explicit, defense-oriented systematization of the browser's low-level attack surface. Prior SoKs have surveyed browser vulnerabilities and mitigation techniques. However, these perspectives remain fragmented, leaving open a central question: how is the low-level attack surface of modern web browsers structured, and which parts of this surface remain underexplored by existing security testing? We approach this primary question through three sub-questions. (RQ1) How is the browser's attack surface structured along input classes and components? (RQ2) Where do memory corruption vulnerabilities arise within this taxonomy? (RQ3) What do these attack-surface patterns imply for existing browser security testing? To answer RQ1, we derive an architecture-grounded Input x Component x Privilege taxonomy that abstracts the architectures of browsers into a unified view. To answer RQ2, we map 2,233 memory corruption reports disclosed between 2016 and 2025 onto this taxonomy. To answer RQ3, we overlay a decade of academic browser fuzzers, classified by the targeted input class, onto the bug-density map. Our systematization reveals that current testing concentrates on well-explored components while bug-dense, high-impact surfaces remain insufficiently tested. Moreover, we identify three fuzzer deployment gaps, which are orthogonal to the academic efforts. Our work offers a structured foundation for future browser security research.

cs.CR↗

arXiv2026

No Hidden Prompts Needed! You Can Game AI Peer Review with Presentation-Only Revisions

As AI-generated reviews move from experimental tools into peer-review infrastructure, most robustness concerns have focused on explicit attacks such as hidden instructions and prompt injection. We study a harder and more policy-relevant failure mode: no hidden text, no prompt injection, and no changes to methods, experiments, figures, equations, proofs, or numerical results. The attacker modifies only presentation-level content, such as the abstract, contribution framing, related work, discussion, and narrative structure. We introduce adversarial repackaging: a closed-loop attack that uses AI-reviewer feedback to search for presentation-level revisions while keeping the scientific evidence fixed. Across three mainstream AI reviewers, adversarial repackaging achieves a 75.1% attack success rate and a mean score gain of +1.21/10. The effect is not explained by ordinary prose polishing. We also reveal that strategies that change how the reviewer interprets the paper, such as related-work repositioning and analytical discussion expansion, substantially outperform surface edits such as local polishing, table formatting, and algorithm boxes. Our analysis reveals two deeper structural failure modes. First, AI reviewers are easier to impress than to convince: highlighting strengths reliably increases perceived merit, while attempts to dissolve weaknesses frequently backfire. Second, AI reviewers can confuse the appearance of addressing a limitation with actually resolving it, allowing unchanged evidence to be reinterpreted as stronger scientific contribution. These results show that the deployment risk is not only malicious hidden instructions, but the emergence of paper presentation itself as an optimization surface. We release a contamination-free rolling benchmark and attack framework for testing whether AI reviewers remain anchored to scientific content under presentation-only edits.

cs.CL↗

arXiv2026

CRANE: Knowledge Editing for Reasoning MLLMs

The emergence of reasoning multimodal large language models (MLLMs), which generate explicit chain-of-thought (CoT) reasoning before producing answers, has introduced a new challenge for knowledge editing: methods that appear successful under traditional metrics (teacher-forcing accuracy up to 100%) can fail severely when the model's reasoning process is examined (Grounded Success as low as 0%). We identify three failure modes: (1) Structural Collapse, where weight-modifying methods destroy the CoT format; (2) Cognitive Dissonance, where the model's reasoning chain actively rejects the injected edit fact based on visual evidence; and (3) Shallow Internalization, where methods succeed on exact queries but fail on rephrase or multi-hop variants. On reasoning MLLMs, these modes interact: methods that generalize (FT, LoRA) trigger format collapse, while methods without deep modification cannot generalize. To expose these failures, we propose a CoT-aware evaluation protocol and construct ReasonEdit-Bench, with conflict stratification, multi-level probes, and multi-hop portability tests. We propose CRANE, a retrieval-augmented framework that requires no per-edit parameter modification. CRANE combines a modality-aware dual-library retrieval system with a two-phase training strategy: Supervised Fine-Tuning (SFT) for structural initialization, followed by GRPO with a Cognitive Routing Reward that trains the model to arbitrate between visual priors and injected edit facts. On ReasonEdit-Bench, CRANE achieves 96.9% Grounded Success on conflict scenarios and 96.9% intermediate entity usage in multi-hop chains, with 97.6% text-locality and 68.1% image-locality Edit Independence. On the out-of-distribution MMEVOKE benchmark, CRANE reaches 87.0% under gold retrieval.

cs.CV↗

arXiv2026

CLFEC: A New Task for Unified Linguistic and Factual Error Correction in paragraph-level Chinese Professional Writing

Chinese text correction has traditionally focused on spelling and grammar, while factual error correction is usually treated separately. However, in paragraph-level Chinese professional writing, linguistic (word/grammar/punctuation) and factual errors frequently co-occur and interact, while many draft-level errors are sparsely observable in published texts after editorial review, making unified correction both necessary and controlled benchmark construction essential. This paper introduces CLFEC (Chinese Linguistic \& Factual Error Correction), a new task for joint linguistic and factual correction. We construct a mixed, multi-domain Chinese professional writing dataset spanning current affairs, finance, law, and medicine. We then conduct a systematic study of LLM-based correction paradigms, from prompting to retrieval-augmented generation (RAG) and agentic workflows. The analysis reveals practical challenges, including limited generalization of specialized correction models, the need for evidence grounding for factual repair, the difficulty of mixed-error paragraphs, and over-correction on clean inputs. Results further show that handling linguistic and factual errors within the same context outperforms decoupled pipelines, and that agentic workflows can be effective with suitable backbone models. Overall, CLFEC provides a new benchmark for Chinese text correction research and practical guidance for proofreading systems.

cs.CL↗

arXiv2026

GAPD: Gold-Action Policy Distillation for Agentic Reinforcement Learning in Knowledge Base Question Answering

Reinforcement learning (RL) is a natural fit for agentic knowledge base question answering (KBQA), where a model must issue executable actions, observe knowledge-base feedback, and eventually return an answer. However, current RL-based KBQA systems mainly optimize sparse rewards from the final answer, leaving intermediate action errors weakly supervised. This is especially limiting for logical-form annotated KBQA benchmarks: gold logical forms can be converted into executable action sequences, but existing pipelines use them mainly for warm-start data construction rather than for on-policy RL updates. We propose GAPD, a training-time Gold-Action Policy Distillation framework that adds dense token-level guidance to outcome-based RL. To align gold actions with on-policy student rollouts, GAPD uses MID-ANCHOR MATCHING: it treats the intermediate entities reached during student exploration and gold execution as state anchors, and matches student states to gold states through these explored entity sets. The current policy conditioned on this aligned gold action serves as a stop-gradient teacher, whose token distribution is distilled back to the ordinary student policy over generated action-token spans. GAPD consistently surpasses the current state of the art on WebQSP, GrailQA, and GraphQ.

cs.CL↗

arXiv2026

Enhanced Fluid Index Modulation for Integrated Data and Energy Transfer

Integrated data and energy transfer (IDET) is a promising technique for supporting sustainable low-power wireless networks. To improve both communication reliability and energy transfer efficiency, this paper investigates a fluid index modulation (FIM) assisted IDET system, where the base station employs a two-dimensional fluid antenna system (FAS) and the receiver adopts a power-splitting architecture. In FIM, the information bits are delivered not only from the modulation symbols, but also the index of antenna position. Under finite-alphabet signaling, the average harvested power, bit error rate (BER), and achievable data rate are derived in closed form. A joint optimization problem is formulated to maximize the average harvested power subject to BER and achievable rate constraints by jointly optimizing the port selection, precoding vector, and power splitting ratio. An alternating optimization framework is developed, where the precoding vector and port selection are obtained via a Riemannian augmented Lagrangian method (RALM) and block coordinate descent (BCD) algorithm, respectively. Simulation results demonstrate that the proposed scheme achieves a superior rate-energy trade-off over benchmark schemes, while the proposed algorithm attains near-optimal performance with significantly lower complexity than exhaustive search.

cs.IT↗

arXiv2026

SEEM: Exploiting Black-Box Text Attacks to Manipulate Tool Selection

Tool learning has emerged as a powerful auxiliary mechanism that extends the capabilities of large language models (LLMs), enabling them to address complex tasks that demand real-time relevance or high-precision operations. However, beneath this strength lie significant security risks. Prior studies have primarily concentrated on corrupting the outputs of invoked tools, while largely overlooking the vulnerability of the tool selection process itself. To bridge this gap, we introduce a black-box, text-based attack that substantially increases the likelihood of a target tool being selected. We propose SEEM, a two-level coarse-to-fine perturbation method that operates at both the word and character levels. Through comprehensive experiments, we show that merely perturbing the textual information of tools can markedly raise the probability of the target tool being prioritized and ranked higher among candidates. Our findings expose critical weaknesses in the tool selection mechanism and lay the groundwork for developing defenses to secure this essential process.

cs.CR↗

arXiv2026

Uncovering Competing Poisoning Attacks in Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) systems improve the factual grounding of large language models (LLMs) but remain vulnerable to retrieval poisoning, where adversaries seed the corpus with manipulated content. Prior work largely evaluates this threat under a simplified single-attacker assumption. In practice, however, high-value or high-visibility queries attract multiple adversaries with conflicting objectives. Motivated by real cases, we introduce the setting of competing attacks, in which multiple attackers simultaneously attempt to steer the same or closely related query toward different targets. We formalize this threat model and propose competitive effectiveness, a metric that quantifies an attacker's advantage under competition. Extensive experiments show that many strategies that succeed in the single-attacker regime degrade markedly under competition, revealing performance inversions and highlighting the limits of conventional metrics such as attack success rate and F1. Furthermore, we present PoisonArena, a standardized framework and benchmark for evaluating poisoning attacks and defenses under realistic, multi-adversary conditions.

cs.IR↗

arXiv2026

Learning When Not to Act: Mitigating Tool Abuse in Agentic Reinforcement Learning

Agentic reinforcement learning can induce tool abuse, where models overuse external tools even for queries solvable by internal reasoning. Existing approaches mitigate this issue with uniform tool-use penalties or hard limits, which reduce tool frequency but may also suppress useful tool-assisted exploration. We propose EAPO, an Efficient Agentic Policy Optimization framework that learns selective tool use. EAPO introduces tool-free trajectories into each rollout group, applies difficulty-aware reward shaping to penalize redundant tool calls mainly on easier queries, and uses confidence-aware token reweighting to improve policy learning. Across nine mathematical and knowledge-intensive reasoning benchmarks, EAPO consistently improves the accuracy efficiency trade-off on Qwen2.5-3B, Qwen2.5-7B, and Llama3.1-8B. Compared with GRPO, EAPO improves average performance by 10.45%, 7.27%, and 9.69%, while reducing average tool calls by 18.33%, 18.33%, and 24.59%, respectively. These results show that agents can learn when not to use tools without compromising tool-integrated reasoning.

cs.AI↗

arXiv2026

EarlyTom: Early Token Compression Completes Fast Video Understanding

Video large language models (Video-LLMs) have demonstrated strong capabilities in video understanding tasks. However, their practical deployment is still hindered by the inefficiency introduced by processing massive amounts of visual tokens. Although recent approaches achieve extremely low token retention ratios while maintaining accuracy comparable to full-token baselines, most of them perform compression only at the late stage of prefilling, leaving the efficiency of the vision encoder unoptimized. In this paper, we first show that vision encoding contributes a large portion to the time-to-first-token (TTFT). Therefore, instead of compressing visual tokens only after the vision encoder, performing compression inside the encoder still leaves substantial room for exploration. Based on this insight, we propose EarlyTom, a training-free token compression framework that performs early-stage visual token compression inside the vision encoder, enabling significantly better TTFT reduction and higher throughput. In addition, we introduce a decoupled spatial token selection strategy that improves the overall compression effectiveness. EarlyTom reduces TTFT by up to 2.65x and FLOPs by up to 61% on a single NVIDIA A100 GPU for the LLaVA-OneVision-7B model, while maintaining accuracy comparable to the full-token baseline. These improvements substantially enhance the practicality of deploying Video-LLMs in real-world production scenarios.

cs.CV↗

arXiv2026

Curriculum-Guided Heterogeneous Multi-Agent Intelligence for Multi-UAV Cooperative ISAC

Seamlessly unifying communication and sensing, sixth-generation (6G) networks are poised to transform into intelligent platforms with high spectral-energy efficiency and real-time environmental awareness. In the low-altitude economy, unmanned aerial vehicles (UAVs) enable air-ground integrated sensing and communication (ISAC) for applications such as logistics and inspection, yet most studies focus on single-UAV or homogeneous-agent designs. In contrast, this paper proposes a multi-UAV cooperative ISAC system that enables heterogeneous-agent collaboration between multiple UAVs and a ground base station (BS) for joint target sensing, tracking, and communication. The system is formulated as a posterior Cramer-Rao bound (PCRB) minimization problem under communication performance constraints, utilizing joint trajectory-beamforming optimization. To tackle the NP-hard nature of this problem, we design a curriculum-based heterogeneous-agent proximal policy optimization (C-HAPPO) algorithm, where curriculum learning guides progressive policy refinement and Kronecker/QR decomposition mitigates action dimensionality. Simulation results show that the proposed approach achieves more than a 30% improvement in sensing performance, faster convergence, and higher tracking accuracy than existing baselines, demonstrating its scalability and effectiveness for complex multi-UAV ISAC scenarios.

eess.SP↗

arXiv2026

Training-Free Looped Transformers

We introduce training-free looped transformers, in which a lightweight inference-time wrapper loops a contiguous mid-stack block of layers of a frozen checkpoint without additional fine-tuning, continued training, or architectural changes. Unlike prior looped transformer methods that train with the looped structure end-to-end, we retrofit recurrence onto pretrained models at test time. We show that naive block reapplication usually degrades performance, highlighting the importance of the loop application strategy. Motivated by viewing a pre-norm transformer block as a forward Euler step on an ODE, we instead treat looping as a refinement of the same approximation, replacing one large update with smaller damped sub-steps. Across seven dense, sparse MoE, and MLA+MoE model families, our method improves Qwen3-4B-Instruct by +2.64 pp on MMLU-Pro, Qwen3-30B-A3B-Instruct by +1.14 pp on CommonsenseQA, and Moonlight-16B-A3B-Instruct by +1.20 pp on OpenBookQA.

cs.LG↗

arXiv2026

CRAFT: Conflict-Resolved Aggregation for Federated Training

The aggregation of conflicting client updates remains a fundamental bottleneck in federated learning (FL) under heterogeneous data distributions. Naive averaging can produce a global update that improves the global objective while conflicting with specific clients, causing degradation for those clients. In this work, we propose CRAFT (Conflict-Resolved Aggregation for Federated Training), a new aggregation framework that treats the global update as a geometric correction problem. We formulate aggregation as finding the update closest to a reference direction while satisfying conflict-free alignment constraints. We derive a closed-form expression for the constrained optimization problem, avoiding the computational overhead of iterative solvers. Furthermore, we use a layer-wise adaptation to address conflicts at varying feature granularities. We provide a theoretical analysis showing that CRAFT promotes a common-descent structure and mitigates conflicts through its projection geometry. Extensive experiments on heterogeneous benchmarks demonstrate that CRAFT improves the accuracy of the global model while reducing performance disparity across clients compared with state-of-the-art baselines. The source code for CRAFT is available at https://github.com/tum-pbs/CRAFT.

cs.LG↗