Searcharxiv⌕ Search

arXiv subjects

Yao Liu

Publications and source records attributed to Yao Liu.

At least 19 recordsLinked to original sources
arXiv2026

Improving Sampling Efficiency in RLVR through Adaptive Rollout and Response Reuse

Group relative policy optimization (GRPO) trains large language models with verifiable rewards by normalizing rewards within response groups. When every response in a group receives the same reward, the advantages vanish and the group provides no policy gradient signal. We propose Adaptive Rollout and Response Reuse Policy Optimization (AR3PO) to obtain informative groups with fewer generations. Adaptive rollout samples responses to each prompt in stages and stops sampling once the model generates a correct response. If all sampled responses are incorrect, response reuse replaces one of them with a past correct response to the same prompt, when available, and recomputes the group advantages. Policy-recomputed reuse trains on the updated groups using probabilities recomputed under the rollout policy; advantage-only reuse uses historical responses only to compute advantages. Across four mathematical benchmarks with 7B and 8B models, AR3PO consistently improves over GRPO and achieves performance comparable to DAPO while requiring up to $4.2\times$ fewer generated responses. Experiments with a 32B model also show comparable performance to DAPO at a similar training stage with substantially fewer generated responses.

cs.LG↗
arXiv2026

Aperture Photometric Accuracy of Point-spread-function-deconvolved Astronomical Images

This paper introduces an improved Richardson--Lucy (RL) framework utilizing negative backfilling (NB) and the novel filtered image deconvolution and noise backfilling (FiDNoBa) algorithm. By integrating a low-pass prefiltering stage---specifically employing a Kalman filter---with the reintegration of filtered-out noise components after RL iterations, we effectively suppress noise artifacts while maintaining rigorous flux integrity. We extensively evaluate our Kalman + RL + NB approach using both numerical simulations and real observational data. Simulations across three regimes demonstrate superior photometric accuracy, reducing the relative mean deviation (RMD) to below 1\% for isolated sources, maintaining high fidelity (RMD $\sim$0.37\%) for blended Sérsic galaxies, and achieving $\sim$5\% RMD in crowded stellar fields while significantly increasing source recovery rates compared to traditional point-spread function photometry. Crucially, we validate the practical efficacy of FiDNoBa on real space-based (JWST/NIRCam) and ground-based (Very Large Telescope Survey Telescope OmegaCAM) images. The results confirm that our method reliably handles complex instrumental signatures, such as the extended wings of the STPSF, mitigating the severe ringing artifacts typical of traditional RL deconvolution while ensuring highly stable aperture photometry in practical survey processing.

astro-ph.IM↗
arXiv2026

Task-Performance Routing for Multi-Teacher Distillation in CT Medical Image Segmentation

Pre-trained models offer complementary strengths in CT organ segmentation, but their relative accuracy varies across organs and spatial regions. Multi-teacher knowledge distillation can combine these strengths in a single student, yet global or instance-level teacher weights overlook variation within a 3D volume. We propose Task-Performance Routing (TPR), which uses region-wise segmentation errors to determine teacher weights during training without learned routing parameters. In hard regions, TPR favors teachers with lower prediction errors; in easy regions, it uses uniform weights to combine their knowledge. A hierarchical spatial partition provides fine-grained routing in shallow encoder stages and coarse-grained routing in deep stages. Experiments on BTCV, MSD-Liver, and MSD-Pancreas with two teacher pairs and two backbone architectures show higher Dice scores than the individual teachers, adaptive ensembles, and evaluated multi-teacher distillation baselines. On MSD-Pancreas, TPR achieves Dice scores of 65.40% with SwinUNETR and 68.25% with U-Net, compared with 64.38% and 67.45% for the corresponding adaptive ensembles. Inference uses the student alone, with no routing or teacher overhead. Code is available at https://github.com/EdvinCecilia/TPR_MultiTeacher.

cs.CV↗
arXiv2026

DyHist: Query-Aware Historical Dynamics Modeling for Temporal Knowledge Graph Extrapolation

Temporal Knowledge Graph (TKG) extrapolation aims to predict future facts from observed historical events. Existing methods usually achieve this goal by jointly modeling local historical evolution and long-range historical contexts. First, local evolution modeling often summarizes local history into an overall evolving representation, where query-relevant local deviations may not be sufficiently exploited as useful predictive features. Second, existing long-range history modeling often treats historical recurrence as a stable cue, while overlooking that its reliability may vary across relations and recent contexts. To address these issues, we propose DyHist, a query-aware historical dynamics modeling framework for TKG extrapolation. DyHist captures local dynamics by separating recent evidence from medium-range contexts and explicitly modeling their query-relevant deviations as predictive features. It further uses a relation-aware historical prior to calibrate candidate scores with time-decayed support, recent trends, and relation-specific strength, enabling recurrence signals to contribute differently across relations and recent contexts. Experiments on four benchmarks show that DyHist achieves the best MRR against recent baselines. Code is available at https://github.com/PANPANKK/DyHist.

cs.IR↗
arXiv2026

MGE-PO: Entropy-Aware Credit Assignment for Mathematical Reasoning

GRPO assigns the same group-relative advantage to equally rewarded responses within a question, leaving their generation uncertainty unused. We introduce MGE-PO, centered on four-quadrant (4Q) advantage shaping that combines verified correctness with rollout generation entropy. Correctness determines the sign of an additional correction, while entropy controls its magnitude: lower-entropy successes receive larger bonuses and higher-entropy failures receive larger penalties. An online entropy-based question curriculum supports this credit rule using cached rollout measurements. At the final checkpoint after eight training epochs on Qwen3-8B-Base, adding 4Q across three policy optimization settings yields absolute gains of 3.23-3.69% in six-benchmark macro avg@32 and 4.24-11.06% in macro pass@32. On Qwen2.5-7B-Base, the complete configuration raises four-benchmark macro avg@32 from 41.5% to 45.4%.

cs.CL↗
arXiv2026

GDEPO: Group Dual-dynamic and Equal-right Advantage Policy Optimization for Sample-Efficient Reinforcement Learning

Automated Theorem Proving (ATP) is a fundamental AI challenge, requiring machine-verifiable proofs in formal languages like Lean to evaluate reasoning. Reinforcement Learning (RL), especially Group Relative Policy Optimization (GRPO), is a mainstream approach. However, GRPO faces two critical issues in ATP: its relative advantage estimation may conflict with binary verifier feedback under composite rewards, and its static sampling strategy discards batches without valid proofs, causing data waste. Repeated training on mastered problems also wastes computation. To address this, we propose Group Dual-dynamic and Equal-right Advantage Policy Optimization (GDEPO), incorporating three core mechanisms: 1) dynamic additional sampling, resampling ineffective batches until a valid proof is found; 2) equal-right advantage, decoupling the advantage function's sign (correctness) from its magnitude (auxiliary rewards) to ensure stable policy updates while increasing effective computation; and 3) dynamic additional iterations, applying extra gradient steps to initially failed but eventually successful samples to accelerate learning. Experiments on MinF2F-test, MathOlympiadBench, and PutnamBench confirm GDEPO's effectiveness, with ablation studies validating its synergistic components. The method enhances data utilization and optimization efficiency, offering a novel training paradigm for ATP.

cs.AI↗
arXiv2026

Disclosure-Gated User Simulation for Companion-Agent Evaluation

Playing the user with a large language model is standard in scalable evaluation, and has a repeatedly diagnosed failure: the simulated user is excessively cooperative, so a system under test can score by the number of questions it asks rather than by making the user willing to speak. We answer with a disclosure gate conditioning information release on the companion agent's behaviour: its state is a ladder of five ordered gates, merged onto three observable depth layers. We specify, ablate, and audit it. The gate is a load-bearing component of the environment: on a published companion-agent benchmark's English corpus, withdrawing per-example gate statements from training displaces the ranking of the 12 systems beyond the noise band of a seed re-run, while per-system scores show no detectable change. We state two acceptance criteria: a ranking must be order-preserving, and absolute scores must be scale-stable. Only one candidate passes both -- the simulator we release -- correlating at 0.993 with the published leaderboard. Prompting a frontier model instead barely moves the ranking while shifting every score up, invisible to ranking-only checks; we supply the specification, ablations, and downstream sensitivity analysis the benchmark's environment lacked.

cs.CL↗
arXiv2026

A Comprehensive Survey of Website Fingerprinting Attacks and Defenses in Tor: Advances and Open Challenges

The Tor network provides users with strong anonymity by routing their internet traffic through multiple relays. While Tor encrypts traffic and hides IP addresses, it remains vulnerable to traffic analysis attacks such as the website fingerprinting (WF) attack, achieving increasingly high fingerprinting accuracy even under open-world conditions. In response, researchers have proposed a variety of defenses, ranging from adaptive padding, traffic regularization, and traffic morphing to adversarial perturbation, that seek to obfuscate or reshape traffic traces. However, these defenses often entail trade-offs between privacy, usability, and system performance. Despite extensive research, a comprehensive survey unifying WF datasets, attack methodologies, and defense strategies remains absent. This paper fills that gap by systematically categorizing existing WF research into three key domains: datasets, attack models, and defense mechanisms. We provide an in-depth comparative analysis of techniques, highlight their strengths and limitations under diverse threat models, and discuss emerging challenges such as multi-tab browsing and coarse-grained traffic features. By consolidating prior work and identifying open research directions, this survey serves as a foundation for advancing stronger privacy protection in Tor.

cs.CR↗
arXiv2026

DASC: Decay-Aware State Compression for Hybrid Linear-Attention Serving

Hybrid linear-attention architectures have recently scaled to large open-weight models, offering quality competitive with full attention while substantially reducing key/value (KV) cache growth. However, their in-place recurrent-state updates complicate cache management: prefix reuse requires state checkpoints alongside full-attention KV, while storing state checkpoints in full increases memory pressure, leading to more evictions and repeated prefill. By analyzing the decay structure of Gated DeltaNet (GDN) and Kimi Delta Attention (KDA), we find that different heads and channels retain prefix information over markedly different timescales, which we term \emph{retention horizons}. This variation suggests substantial compression potential in persistent state checkpoints. Building on this observation, we introduce \emph{Decay-Aware State Compression} (DASC), which derives retention horizons from model weights, selects long-horizon state units, and packs them into a ragged state checkpoint layout. To integrate efficiently with tensor-parallel inference engines, DASC furtherly balances compressed state checkpoints across TP ranks. On reuse, DASC either zero-fills omitted units or refreshes them from a bounded suffix with additional compute cost. Across retrieval and end-to-end reasoning benchmarks on Kimi-Linear, conservative DASC configurations remain close to full caching while compressing KDA recurrent state checkpoints by $2.63\times$. Under fixed state checkpoint memory budgets, the resulting capacity gains reduce mean Time to First Token (TTFT) by 42.6\% and improve input throughput by 68.4\%. At larger compression ratio, suffix refresh recovers much of the accuracy lost to more aggressive omission, at the cost of additional replay computation. Qwen with GDN exhibits a similar quality--efficiency trend, showing that DASC extends from channel-wise KDA to head-wise GDN.

cs.LG↗
arXiv2026

Residual Visual Credit Optimization: Conserved Evidence Routing for Multimodal Reinforcement Learning

Reinforcement learning with verifiable rewards scales multimodal reasoning, but an outcome reward says how much a trajectory is worth, not how that value should be spread over the decisions that produced it. We introduce Residual Visual Credit Optimization (RVCO), which treats token credit as a conserved routing problem. A controlled visual intervention yields a per-token evidence response; robust within-trajectory coordinates remove incidental scale; and a budgeted entropic router distributes a fixed amount of sequence utility according to perceptual dependence. A residual support path guarantees positive credit at every valid position, and an analytic correction restores the prescribed credit mass exactly. The resulting field is selective, bounded, full-support, and invariant to response-local score shifts, and recovers hard token selection as a limiting case. Across four model families and seven reasoning benchmarks, RVCO improves accuracy over strong RLVR baselines while maintaining late-stage optimization stability, corruption robustness, and competitive training cost. Rewards, rollouts, and the group-relative advantage estimator are unchanged; only the geometry of token-level credit differs.

cs.LG↗
arXiv2026

The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends

Self-attention gives LLMs fine-grained, query-dependent access to context, but dense token interactions incur quadratic prefill cost and a key--value cache growing with context length. Research thus spans explicit-memory compression, sparse access, recurrent state construction, structured state dynamics, and heterogeneous mechanism composition. This survey analyzes these developments as model-internal contextual memory. We introduce a five-dimensional lens---Memory Representation, Memory Update, Access, Readout, and Integration---describing what is represented, how it changes, what is query-eligible, how it is read, and how readouts form outputs. This lens compares overlapping research lines without imposing one computational model. We reconstruct mechanism-level developments and architectural adoption using 59 release-level records from 14 major model lineages and 11 high-performing open-weight endpoints. First, explicit-memory and recurrent-state methods retain distinct interfaces but increasingly control overlapping memory functions. Second, heterogeneous architectures increasingly coordinate across network depth: layer-wise composition distributes complementary memory processing across representational stages, while cross-layer reuse carries selected memory and routing artifacts forward. Depth thus becomes a dimension along which contextual memory is constructed and managed. Third, these developments motivate a stateful multidimensional memory-routing hypothesis: persistent memory is organized across temporal scope, network depth, substrate type, and representation granularity, while coordinated Sparse Write and Sparse Read determine what is maintained and what contributes to each query. Overall, efficient sequence architecture design increasingly concerns the organization, lifecycle, and selective use of contextual memory rather than an isolated Attention operator.

cs.CL↗
arXiv2026

From Experts to Sub-experts: Fine-grained Parameter-Efficient Fine-Tuning for MoE LLMs

As large language models (LLMs) scale rapidly, dense full-parameter adaptation becomes increasingly expensive, motivating sparse and modular architectures such as Mixture-of-Experts (MoE) models. This shift raises a key question for parameter-efficient fine-tuning (PEFT): at what granularity should parameters be selected and updated? Existing PEFT methods such as LoRA operate on predefined weight matrices, while expert-level sparse tuning methods update entire selected experts. However, we observe that activated experts are internally sparse, with only a small fraction of intermediate channels strongly responding to downstream tasks, indicating that expert-level adaptation is still too coarse. We propose NSFT (Neural Sub-expert Fine-Tuning), a fine-grained PEFT framework that refines MoE adaptation from experts to sub-experts. NSFT decomposes each expert along the intermediate dimension into structured channel groups and selects task-relevant sub-experts by combining routing importance with intra-expert activation saliency. To optimize sparse partial updates, NSFT further introduces learning-rate scaling and dynamic gradient scaling to compensate for the reduced effective update magnitude. Experiments on OLMoE and Ling-mini-2.0 across challenging domain-specific tasks and general benchmarks show that NSFT consistently outperforms representative PEFT and expert-level sparse tuning baselines, while using substantially fewer trainable parameters and preserving competitive general capability. These results suggest that sub-expert-level adaptation is a more precise and efficient PEFT paradigm for MoE LLMs.

cs.LG↗
arXiv2026

Chameleon: Robust Defense Against Tor Website Fingerprinting via Many-to-Many Traffic Morphing

Website fingerprinting (WF) attacks can infer users' browsing activities from encrypted Tor traffic by exploiting side-channel features. Although many WF defenses have been proposed, we find that most existing defenses create learnable web trace mapping features. We further show that robustness against adversarial training does not necessarily imply robustness against defense-aware autoencoder (DAAE)-based attacks. To address these limitations, we present Chameleon, a robust WF defense based on many-to-many randomized traffic morphing. Chameleon selects morphing candidates with high intra-class diversity and low inter-class disparity. Chameleon randomly maps each webpage trace to multiple candidates, and allows different webpages to share morphing targets, thereby increasing adversarial uncertainty. For practical Tor deployment, Chameleon introduces a radix-trie-based synchronization mechanism that enables pluggable transport (PT) endpoints to identify consistent morphing traces using packet-direction prefixes, together with trace mutation and normalized prefix matching to reduce overhead. We evaluate Chameleon against six state-of-the-art defenses and five WF attacks on three public datasets in closed- and open-world settings. Compared with Adaptive Tamaraw, Chameleon reduces adversarial-training-based attack accuracy by up to 36.74% while reducing bandwidth and time overhead by 34.12% and 60.38%, respectively. Under DAAE-based RF attacks on GTT23, Chameleon limits attack performance to 35.19% F1-score while Adaptive Tamaraw only limits it to 88.22% F1-score. In the real-world PT bridge evaluation, Chameleon substantially reduces the effectiveness of strong WF attacks while incurring only 16.25% time overhead.

cs.CR↗
arXiv2026

Hot water emission during an outburst in a classical T Tauri star

In this paper, we present observations of an eruptive young star in the Rosette Nebula, identified by the Gaia Science Alerts system using Gaia time series data. We aim to investigate the evolution of the brightness and mass accretion rate of V557 Mon throughout its outburst and subsequent decline. In addition, we trace the evolution of the inner accretion disk during the outburst by monitoring molecular emission features. We compiled multi-band photometric time series from Gaia, ZTF, and several 1 m-class ground-based telescopes and obtained optical and near-infrared spectra at multiple epochs covering the outburst and fading phases. Stellar parameters were derived from quiescent colour/spectra and spectral energy distribution (SED) fitting. We also measured the mass accretion rate and fit models to molecular emission bands. Since late 2024, V557 Mon has undergone a year-long outburst consistent with EXor variability. Based on quiescent photometry, V557 Mon has a spectral type of M1 with an extinction of AV = 1.8+_0.3 mag, consistent with a 0.4-0.5 M_sol star at an age of 2 Myr. Our multi-epoch spectra and u-band photometry indicate a peak accretion rate of 6.3x10^(-7)M_sol/yr during the outburst, roughly 70 times higher than in quiescence. We report the detection of hot water vapour emission bands, together with TiO, VO, and CO emission features. Using ExoMol models, we measured the inner-disk temperature changed from 3000 K to 2000 K during the fading phase of the outburst. We report a recent EXor outburst in a low-mass Class II YSO. Our observations reveal the transient formation of a hot molecular inner disk, traced by variable water vapour emission during the EXor event. A positive correlation is found between the molecular excitation temperature and the overall stellar brightness.

astro-ph.SR↗
arXiv2026

CompanionBench: A Theory-Anchored, Real-World-Grounded Benchmark for AI Emotional Companionship

LLM companions are deployed at scale in personally consequential settings, yet poorly evaluated. Existing benchmarks use hand-authored scenarios and prompted simulators, aggregate empathy into one score, and overlook judge biases such as same-family favoritism and scale drift. We introduce CompanionBench, an interactive bilingual benchmark. To our knowledge, it is the first companion benchmark to ground both its scenarios and a trained user simulator in de-identified real-world data. A hidden disclosure gate branches each persona's trajectory on the agent's own behavior, controlling the interaction state space without scripting dialogue. We operationalize ten capabilities derived from 25 theories across psychology and counseling, four of them not graded explicitly by prior work: holding ambiguity, selfobject responsiveness, positive resonance and calibrated challenge. Agents are assessed on two complementary axes: a subjective ten-capability rubric and a deterministic measure of whether deeper disclosure was earned. A cross-family panel dilutes same-family favoritism; an Item Response Theory model separates agent quality from judge severity. Theory fixes what to measure and how personas are structured; real data supply events, history, and profiles -- coverage from theory, authenticity from data. Rankings are reproducible in both languages (rho = 0.996 ZH / 0.953 EN). Evaluating 28 agents reveals capability-level differences obscured by aggregate scores. Emotion regulation and calibrated challenge remain common weaknesses; holding ambiguity discriminates most. Role-play agents rank near the bottom: immersion does not imply relational competence. Across agents, the dominant failure mode is substituting surface warmth for substantive relational support. We will release 500 Chinese-English parallel pairs and the evaluation code.

cs.CL↗
arXiv2026

Large Language Models and Social Media Information Integrity: Opportunities, Challenges, and Research Directions

Large Language Models (LLMs) have emerged as powerful tools that impact information integrity on social media platforms. This comprehensive review examines the dual role of LLMs in both facilitating and mitigating various information integrity challenges, including misinformation, disinformation, fake news, social bots, and privacy concerns. \textcolor{black}{We conduct a comprehensive review of the literature from 2019 to 2024, screening 1048 studies and performing an in-depth analysis of 215 representative papers. This systematic approach allows us to identify key patterns in how LLMs influence the information security in social media ecosystems.} Through a systematic analysis of papers from multiple databases, our findings reveal that while LLMs can enhance detection capabilities for malicious content and enable sophisticated defense mechanisms, they simultaneously pose risks by enabling the generation of highly convincing, deceptive content. We categorize and analyze the potential and challenges across different dimensions of information integrity, examining technical capabilities, ethical implications, and privacy concerns. The study demonstrates critical gaps in current approaches, particularly in cross-lingual detection, real-time monitoring, and privacy-preserving implementations. We conclude by proposing future research directions and recommendations for stakeholders to leverage LLMs while mitigating risks in social media information integrity.

cs.CR↗
arXiv2026

Fenced Citation-Context Retrieval for Case Law: Temporal Leakage and Degree Control Across Two Jurisdictions

Prior case retrieval (PCR) aims to identify the precedent cases relevant to the facts of a query case. Incoming citation context, the text with which later cases characterize a case when citing it, is a powerful relevance signal, yet it is typically evaluated without a temporal constraint, so the retriever is credited with citations made after the query. We introduce a temporally fenced retriever with no learned parameters that augments BM25 with incoming citation context restricted to citations predating the query, together with a temporal-admission decomposition that quantifies the phantom fraction: the share of a citation-context gain attributable to citations not known to predate the query. Experiments span two jurisdictions, U.S. federal (CLERC) and European (ECtHR-PCR) case law. On ECtHR-PCR, without any training, the fenced retriever outperforms a strong degree-controlled baseline across the full recall ladder, and a temporal-admission decomposition attributes 14.9% (validation) of an unfenced citation-context gain over BM25 to citations not known to predate the query. Citation-context retrieval must therefore be temporally fenced and degree-controlled before its reported gains can be interpreted.

cs.IR↗
arXiv2026

Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM

Large Language Models (LLMs) have revolutionized content creation across digital platforms, offering unprecedented capabilities in natural language generation and understanding. Meanwhile, they pose risks by inadvertently producing toxic, offensive, or biased content. This dual role of LLMs, both as powerful tools for text generation and as potential sources of harmful language, presents a pressing sociotechnical challenge. In this survey, we systematically review recent studies encompassing unintentional toxicity, adversarial jailbreak attacks, and comprehensive mitigation strategies. We explore LLMs' dual role as both generators of harm and enablers of safety through detection, classification, content moderation, and prevention. We propose a unified taxonomy of LLM-related harms and defenses, analyze emerging multimodal and LLM-assisted jailbreak strategies, and assess mitigation efforts, including reinforcement learning with human feedback (RLHF), prompt engineering, and safety alignment. Our review highlights the evolving landscape of LLM safety and identifies limitations in current evaluation methodologies. Ultimately, our review outlines future research directions to guide the development of robust and ethically aligned language technologies.

cs.CL↗