Search arXiv⌕ Search

arXiv subjects

Chang Liu

Publications and source records attributed to Chang Liu.

At least 181 records · Page 10Linked to original sources
arXiv2026

Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results

AI evaluations are widely used for testing and understanding progress. However, the diverse evaluators bring with them inconsistencies that challenge analysis and comparison. First, results are saved in incompatible formats, scattered across leaderboards, papers, blog posts, evaluation harness logs, and custom repositories. Second, results are created by different evaluation frameworks, which produce divergent scores for nominally identical evaluations and record metadata inconsistently, hindering comparison, cross-community evaluation science, cost reduction, and reuse. We introduce Every Eval Ever, the first shared schema and community-crowdsourced repository for AI evaluation results. The schema standardizes how evaluations are represented in a unified, single JSON document. It is source-agnostic by design, ingesting results from evaluation harnesses and papers alike, and optionally stores per-instance outputs for fine-grained analysis. We contribute: (i) a community-governed metadata schema with a companion instance-level schema, the first standardization effort of its kind; (ii) automatic converters from popular formats, evaluation harnesses, and leaderboards to the unified schema; and (iii) a crowdsourced community database hosted on Hugging Face, currently spanning to date 22,235 models, 2,273 unique benchmarks, and 31 evaluation formats.

cs.AI↗
arXiv2026

JWST Spectroscopy of SN Ia 2022aaiq and 2024gy: Evidence for Enhanced Central Stable Ni Abundance and a Deflagration-to-Detonation Transition

We present optical + near-infrared (NIR) + mid-infrared (MIR) observations of the normal Type Ia supernovae (SN Ia) 2022aaiq and 2024gy in the nebular phase, continuously spanning 0.35-28 microns. Medium-resolution JWST spectroscopy reveals novel narrow ($v_{\mathrm{FWHM}}<1500$ km s$^{-1}$) [Ni II] 1.94 and 6.64 micron cores in both events. The MIR [Ni II] 6.64 micron line exhibits a distinct narrow core atop a broader base, indicating a central enhancement of stable Ni. This structure points to high central densities consistent with a near-Chandrasekhar-mass ($M_{\text{Ch}}$) progenitor or a high-metallicity sub-$M_{\text{Ch}}$ progenitor. From detailed line-profile inversions of SN 2024gy, we derive emissivity profiles for stable iron-group elements (IGEs), radioactive material, and intermediate-mass elements (IMEs), revealing spatially distinct ejecta zones. The [Ni III] 7.35 micron line shows a shallow-to-steep slope transition - a "broken-slope" morphology - that matches predictions for delayed detonation explosions with separated deflagration and detonation ashes. We also reanalyze and compare to archival JWST spectra of SN 2021aefx and the subluminous SN 2022xkq. From the stable Ni luminosities, we infer that SN 2024gy produced ~5-10 times more stable Ni mass than SN 2022xkq, favoring a near-$M_{\text{Ch}}$ scenario for SN 2024gy and sub-$M_{\text{Ch}}$ scenario for SN 2022xkq. These results demonstrate that resolved line profiles, now accessible with JWST, provide powerful diagnostics of explosion geometry, central density, and progenitor mass in SN Ia.

astro-ph.HE↗
arXiv2026

PAPEL: A Collaborative System for Parental Guidance during Preschool Play-Based English Learning

Play-based parent-child interaction offers preschoolers rich opportunities for everyday foreign language learning, yet many parents struggle to turn open-ended play into effective English-as-a-Foreign-Language (EFL) learning experiences at home. To explore how AI might support this process, we conducted formative studies through interviews and a Wizard-of-Oz study. We identified four key challenges: content selection, language expression, balancing instruction and play, and problem solving. To address these challenges, we present PAPEL, a parent-AI collaborative system that grounds suggestions in the ongoing play scene and organizes support into four core modules: content generation, language adaptation, balance assessment, and extended response. In a counterbalanced within-subjects study with 16 parent-child dyads, PAPEL was associated with more integrated parent utterances that combined playful and instructional content, as well as more parent-child conversational turns, than the lightweight chatbot baseline used in our study.

cs.HC↗
arXiv2026

Boosting Graph Robustness Against Backdoor Attacks: An Over-Similarity Perspective

Graph Neural Networks (GNNs) have achieved notable success in tasks such as social and transportation networks. However, recent studies have highlighted the vulnerability of GNNs to backdoor attacks, raising significant concerns about their reliability in real-world applications. Despite initial efforts to defend against specific graph backdoor attacks, existing defense methods face two main challenges: either the inability to establish a clear distinction between triggers and clean nodes, resulting in the removal of many clean nodes, or the failure to eliminate the impact of triggers, making it challenging to restore the target nodes to their pre-attack state. Through empirical analysis of various existing graph backdoor attacks, we observe that the triggers generated by these methods exhibit over-similarity in both features and structure. Based on this observation, we propose a novel graph backdoor defense method SimGuard. We first utilizes a similarity-based metric to detect triggers and then employs contrastive learning to train a backdoor detector that generates embeddings capable of separating triggers from clean nodes, thereby improving detection efficiency. Extensive experiments conducted on real-world datasets demonstrate that our proposed method effectively defends against various graph backdoor attacks while preserving performance on clean nodes. The code will be released upon acceptance.

cs.LG↗
arXiv2026

Spin correlations in La$_3$Ni$_2$O$_7$ thin films

The discovery of ambient-pressure superconductivity with $T_{c,\text{onset}} > 40$ K in La$_3$Ni$_2$O$_7$ (LNO) thin films grown on the SrLaAlO$_4$ (SLAO) substrate with compressive ($\varepsilon\approx-2\%$) epitaxial strain provides a unique platform for investigating the superconducting mechanism in nickelate superconductors. Here, we use resonant inelastic X-ray scattering (RIXS) to unveil the dispersive spin excitations in the LNO/SLAO thin film and establish the strain dependence of the electronic and spin excitations in LNO thin films with strain ranging from $\varepsilon\approx-2\%$ to $+1.9\%$. Compared with bulk LNO, LNO/SLAO exhibits similar $dd$ excitations and spin dynamics, but with a larger spin-excitation bandwidth, whereas tensile-strained LNO/SrTiO$_3$ exhibits a marked suppression of both the spin excitations and the Ni $3d_{z^2}$-derived $dd$ excitations. This evolution reflects a strain-tuned interlayer exchange interaction $J_z$ and Ni $3d_{z^2}$-O 2$p_z$ hybridization. Our results demonstrate how epitaxial strain modulates the interlayer magnetic coupling and are consistent with scenarios in which the interlayer antiferromagnetic superexchange interaction promotes interlayer pairing in bilayer nickelates.

cond-mat.supr-con↗
arXiv2026

Doping evolution of spin excitations in La$_{3-x}$Sr$_{x}$Ni$_2$O$_7$/SrLaAlO$_4$ superconducting thin films

Ambient-pressure superconductivity in compressively strained bilayer nickelate films provides a unique platform to test pairing scenarios, yet the evolution of magnetism with carrier doping remains largely unexplored. Here, we utilize Ni $L_3$-edge resonant inelastic x-ray scattering to systematically track the evolution of spin and electronic excitations in coherently strained La$_{3-x}$Sr$_x$Ni$_2$O$_7$/SrLaAlO$_4$ thin films, spanning the superconducting ($x \le 0.21$) and overdoped non-superconducting ($x = 0.38$) regimes. We reveal that dispersive spin excitations, characterized by double-stripe correlations and nearly doping-independent exchange scales, persist robustly throughout the entire superconducting dome. In stark contrast, upon entering the overdoped non-superconducting state, this coherent magnetic framework undergoes an abrupt collapse, melting into a heavily damped, low-spectral-weight continuum. We show that this magnetic breakdown is fundamentally driven by a selective doping-induced orbital reconstruction. While the invariant $\sim\!1.0$~eV intra-atomic $dd$ peak confirms an intact local octahedral crystal field, the concurrent quenching of the $\sim\!0.4$~eV and $\sim\!1.6$~eV features signifies a severe degradation of the apical-oxygen-mediated $d_{z^2}$--$p_z$--$d_{z^2}$ singlet sector and bilayer charge-transfer coherence. The synchronized demise of coherent spin excitations and macroscopic pairing establishes a direct, doping-controlled link, underscoring that maintaining the localized $d_{z^2}$ magnetic framework and robust apical-oxygen coupling is the fundamental prerequisite for high-$T_c$ superconductivity in bilayer nickelates.

cond-mat.supr-con↗
arXiv2026

Report on CHIIR 2026 Workshop on Generative AI and Academic Search (GAI&AS)

This report summarizes the CHIIR 2026 Workshop on Generative AI and Academic Search (GAI\&AS), which examined how GenAI is reshaping academic search systems and research practices. The workshop brought together researchers in human information interaction and information retrieval to explore key challenges and opportunities in designing and evaluating future academic search systems that integrate GenAI, moving beyond traditional document retrieval to support summarization, recommendation, synthesis, and conversational interaction. Participants' interests and discussions focused on three thematic clusters: foundations and principles, applications and opportunities, and search-as-learning. Across these themes, the workshop highlighted the importance of academic search systems in supporting transparency, credibility, research integrity, and long-term scholarly needs, as well as in fostering higher-order cognitive processes. Participants discussed guiding theories, design principles, methodological approaches, partnerships, and community-building efforts aimed at advancing human-centered GenAI-enhanced academic search systems. Overall, the workshop demonstrated strong community interest and a diverse range of ongoing and emerging research initiatives at the intersection of GenAI and academic search.

cs.IR↗
arXiv2026

GIFT: LLM-Guided State-Reward Interface for Financial Reinforcement Learning

Financial portfolio trading is naturally formulated as a reinforcement learning problem, where an agent sequentially rebalances assets under changing market conditions to balance return, risk, and transaction costs. Yet in non-stationary markets, raw OHLCV states and short-horizon return rewards often provide an under-specified learning interface, motivating large language models as a way to inject financial knowledge into state and reward design while constraining open-ended generation. To this end, we propose GIFT, an LLM-guided framework for state-reward interface design in PPO-based financial reinforcement learning. Rather than using the LLM to make trading decisions, GIFT uses Factor-guided State Enhancement to generate state features from financial-factor primitives, Risk-rule-guided Reward Shaping to generate auxiliary rewards from portfolio-risk rules, and Diagnostic-guided Refinement to revise candidate interfaces using PPO rollout diagnostics. After refinement, GIFT fixes the selected state-reward interface before evaluation, with no further LLM queries or interface updates at test time. Comprehensive rolling-window experiments across diverse market regimes and portfolio scenarios demonstrate that GIFT improves learning-signal quality and out-of-sample risk-adjusted portfolio performance over baselines. Code and data are available at: https://github.com/KAG778/GIFT .

cs.AI↗
arXiv2026

Quantum resource localizability transitions in deep thermalization

We investigate how quantum resource constraints affect deep thermalization, the emergence of universal local wavefunction distributions from partial measurements of a quantum many-body state. Quantum resources, such as non-stabilizerness (magic), coherence, asymmetry, imaginarity, and non-Gaussianity, are essential for quantum information processing, and constraints on their global abundance can reshape these emergent distributions. To address this question, we develop a unified framework for deep thermalization within general quantum resource theories (QRTs). Our central result is that QRTs fall into two classes: ``smoothly localizable'' (SL) QRTs, where the resource content of local post-measurement states changes continuously with the global resource density, set by the initial state and measurement basis, yielding continuously tunable wavefunction distributions; and ``threshold localizable'' (TL) QRTs, where the local resource content jumps discontinuously from minimal to near-maximal past a critical global resource threshold, producing a sharp transition between a resourceless, ``deep-ergodicity breaking'' distribution and a resourceful, maximally random one. We trace this SL-TL dichotomy to an information-theoretic mechanism, block sharpening: by viewing each QRT as coherence between blocks in Hilbert space, we show that the local resource content depends on the measurement's ability to collapse an initial superposition into a single resourceless block. Our theory is analytically tractable and quantitatively predicts the phase boundaries across all studied QRTs, which we validate with extensive numerical simulations. Finally, we highlight two consequences: a novel magic transition in zero-rate quantum error-correcting codes--previously believed to occur only at finite rates--and new implications for quantum resource certification protocols based on post-measurement state ensembles.

quant-ph↗
arXiv2026

Multimodal Drivers' Emotion Recognition and Safety-Oriented Intervention for Intelligent Transportation Systems

Driver emotions can affect risk perception, decision-making, and vehicle control under complex road conditions. Existing studies mainly focus on driver emotion recognition, while limited attention has been given to context-aware intervention that jointly considers driver emotion and road perception. This paper proposes a safety-prioritized multimodal driver assistance framework that analyzes speech-derived emotional cues and visual road conditions to generate structured driving interventions. The framework first provides road safety reminders and then generates emotion-aligned verbal support. We construct a multimodal dataset by aligning emotional speech signals with structured road environment descriptors and introduce the CARE (Context-Aware Road-Emotion Evaluation) score to jointly evaluate emotion recognition, risk identification, and intervention generation. Experimental results show that the proposed framework balances environmental risk reporting and emotion-aware verbal regulation, providing a feasible safety-driven direction for intelligent transportation systems.

cs.HC↗
arXiv2026

SentinelRAG: Synthetic Sentinel Knowledge for RAG Database Copyright Protection

Protecting proprietary RAG databases from unauthorized redistribution is challenging: existing watermarking methods either inject fabricated relations between real entities, polluting the knowledge base with misinformation, or embed fragile lexical patterns that adversarial paraphrasing easily removes. We propose SentinelRAG, a watermarking framework that embeds style-consistent but fictitious knowledge entries into the RAG database. Our key insight is that synthetic knowledge describing fictitious entities is unlikely to be retrieved by legitimate queries, yet can be reliably triggered through targeted probes known only to the data owner. Experiments on four datasets ranging from 2.9k to 8.8M documents demonstrate that SentinelRAG achieves statistically significant detection $p < 10^{-5}$ across all tested configurations at only a 0.1% injection rate. Compared to the state-of-the-art, our method significantly reduces the false detection rate while maintaining negligible interference with legitimate user queries.

cs.CR↗
arXiv2026

YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition

Large language models (LLMs) drive significant financial innovations, yet their high-concurrency deployment is severely bottlenecked by KV cache memory overhead, which inflates infrastructure costs and throttles scalability. To address this, we propose YouZhi-LLM, a highly efficient financial LLM empowered by a comprehensive structural transition and training pipeline natively built on the Huawei Ascend ecosystem. At its algorithmic core, YouZhi-LLM features a layer-adaptive GQA-to-MLA transition framework that dynamically assigns per-layer FreqFold sizes, maximizing KV-cache compression while minimizing perplexity degradation. To recover representation capacity and inject domain expertise, the Ascend-based training pipeline seamlessly integrates generalized knowledge distillation with financial-specific supervised fine-tuning. Evaluations demonstrate the superiority of this systematic approach, with the adaptive transition reducing perplexity degradation by up to 35% over uniform baselines. Crucially, when evaluated on Ascend NPUs via vLLM-Ascend, the massive KV-cache reduction translates directly into deployment efficiency. Compared to their respective base models, YouZhi-7B yields a 12.3% improvement in average financial benchmark score alongside a 2.69$\times$ increase in maximum concurrency; similarly, YouZhi-14B achieves a 7.0% accuracy gain and a 2.43$\times$ concurrency boost, establishing a new paradigm for cost-effective, high-throughput financial inference.

cs.CL↗
arXiv2026

Steering LLM Viewpoints through Fabricated Evidence Injection

As chatbots increasingly influence daily decision-making, their potential to produce misleading responses poses substantial risks to users. This paper investigates a critical cognitive vulnerability in LLMs: their tendency to uncritically trust external context when presented with fabricated evidence bearing markers of credibility. We introduce Ghostwriter, a two-phase attack framework that first repackages misleading statements with fabricated rationales, then instruct target LLMs to incorporate these viewpoints when responding to relevant queries. Experiments on BBQ, ToxiGen, and our specialized dataset reveal that commercial LLMs without external safety classifiers remain highly vulnerable, while even frontier classifier-guarded models (e.g., GPT-5.4) reduce but do not eliminate the attack. Building on this, we explore multiple defense strategies, among which a tailored safety policy enables gpt-oss-safeguard to achieve 81% detection rate.

cs.CR↗
arXiv2026

A Disappearing Act: Constraints From "Missing" Flares of Repeating Partial TDE Candidates

Recurrent tidal disruption events (rTDEs) are sources that exhibit multiple TDE-like flares; many are likely powered by the recurring partial disruption of a bound star, in a repeating partial TDE (rpTDE). Two such sources, TDE 2022dbl (ASASSN-22ci) and TDE 2020vdq (ZTF20acaazkt), each exhibited two UV/optical flares and, under the assumption of periodicity, both were expected to exhibit a third flare in early 2026. Neither exhibited such a flare, to limits of $L_{\textrm{UV/optical}} \lesssim 10^{42}$ erg s$^{-1}$, $\sim$30$\times$ fainter than the previous flares. Here, we examine several possible explanations. Observing two independent TDEs from the same galaxy within $\sim$2 yr has a probability of $\lesssim$0.5% for measured average TDE rates and currently expected rate enhancements, unless there is extreme intrinsic dispersion in the rates. Theoretical predictions for a double TDE of both stars in a binary are inconsistent with the observed flares. We therefore conclude that TDE 2022dbl and TDE 2020vdq are rpTDEs. To produce only two observable flares with similar energetics, our semi-analytical modeling strongly favors a main-sequence star promptly placed on a bound orbit with a deep initial tidal encounter at pericenter. These results suggest that the majority of rTDEs with multiple flares over a few-year baseline are likely to be rpTDEs, and that a significant fraction of systems may produce only two observable flares. This has important implications for the use of r(p)TDEs as probes of TDE physics and dynamical processes in the nuclei of other galaxies, in addition to the expected yield from upcoming surveys.

astro-ph.HE↗
arXiv2026

When Clients Stop Following: A Cognitive Conceptualization Diagram-driven Framework for Strategic Counseling

Large Language Models (LLMs) show promise in psychological counseling, yet existing benchmarks rely heavily on highly cooperative simulated clients. We observe a critical counselor-following phenomenon: these clients often rapidly shift from resistance to compliance after only a few turns, creating an illusion of therapeutic progress and inflating scores under current evaluation protocols through superficial empathy. To address this evaluation mismatch, we propose a Cognitive Behavioral Therapy (CBT)-grounded resistance-aware framework. We introduce CARS, a client simulator that explicitly models dynamic resistance via Cognitive Conceptualization Diagrams (CCDs). We present STREAMS, a dual-module framework that decouples strategic reasoning (Thinker) from response generation (Presenter) and optimizes it via reinforcement learning. We further propose EWTS-MI, an entropy-weighted metric for evaluating responsiveness under high-friction interactions. Experiments across resistant and non-resistant counseling settings validate our findings on evaluation mismatch and demonstrate the effectiveness of resistance-aware training for improving strategic robustness under challenging counseling interactions.

cs.CL↗
arXiv2026

DMT-CBT: Longitudinal Therapeutic State Modeling for CBT Counseling

Large language models (LLMs) have shown growing potential for Cognitive Behavioral Therapy (CBT) counseling. However, most existing approaches still formulate counseling as a local response generation problem, focusing on empathetic replies within short, text-only, or single-session interactions. We argue that this formulation fundamentally mismatches the nature of real psychotherapy. In clinical CBT, therapy is a longitudinal process in which therapists continuously infer, update, and intervene on evolving therapeutic states across sessions. Realistic CBT further involves multimodal inference and delayed cross-session intervention effects, requiring models to capture longitudinal therapeutic state evolution under partial observability. We propose DMT-CBT, a framework for Dynamic Modeling of evolving Therapeutic states in CBT counseling. DMT-CBT maintains structured therapeutic states across sessions while incorporating multimodal behavioral grounding and tool-augmented intervention to support adaptive therapeutic reasoning. Based on this framework, we construct DMTCorpus, a synthetic multi-session multimodal CBT counseling dataset featuring evolving therapeutic states, image-grounded client behaviors, and cross-session intervention continuity. Experimental results show that DMT-CBT improves counseling fidelity and therapeutic alliance, produces more favorable longitudinal affective trajectories, and preserves therapeutic states more faithfully than post-hoc extraction approaches.

cs.CL↗
arXiv2026

An analysis of the Type Ia SN 2024gy and a comparison of different host extinction estimation techniques

Type Ia supernovae (SNe Ia) are well-known standardisable candles, and are one of the main ways to measure the distance to their host galaxies. However, extinction due to interstellar dust causes objects to appear fainter and redder. Correcting for this requires estimating the amount of intervening material and how the extinction changes as a function of wavelength. We present and analyse optical and near-infrared data of the well-observed SN 2024gy and use these to compare different extinction estimation techniques, making use of photometric, spectroscopic, and polarimetric data. SN 2024gy is a normal SN Ia with high velocity (HV) components in Si II $\lambda6355$ (phase $<-10$ days) and a particularly strong HV feature in the Ca II near-infrared triplet (up to peak). Modelling SN 2024gy with TARDIS shows better matches with a double-detonation scenario compared to a delayed-detonation scenario due to a better match to the Ca II HV component. A measurement of the stable Ni/Fe ratio however favours a delayed-detonation scenario. Host extinction estimates range from $E(B-V)_{host}=0.12\pm0.02$ mag (narrow interstellar absorption lines) to $E(B-V)_{host}=0.24\pm0.06$ mag (Lira law) with a mean of $E(B-V)_{host}=0.22\pm0.04$ mag, assuming $R_V=3.1$. The spread between different methods highlights the challenge of accurately estimating the amount of extinction light suffers before being observed.

astro-ph.GA↗
arXiv2026

The Devil is in the Spectrum: Mitigating Representation Collapse in LLMs via Topologically Regularized Side-Path

Large Language Models (LLMs) are fundamentally limited by representation collapse, a bottleneck that severely degrades long-context performance. We identify that existing approaches risk drifting into one of two pathological extremes: homogenization collapse (e.g., attention sinks causing rank deficiency) and isolation collapse (e.g., local attention causing context disconnection). Through spectral analysis of attention dynamics, we derive an intrinsic trade-off between mixing efficiency (spectral gap) and information capacity (effective rank) that standard mechanisms struggle to balance. To resolve this dilemma, we propose the Topologically Regularized Side-Path (TRSP), a non-invasive architectural intervention that achieves spectral balance. TRSP employs a parameter-free Triangular Box mechanism, scaled by a lightweight, length-aware gate, to regularize the token interaction topology. By integrating proximal coupling to preserve effective rank and distal propagation to support non-degenerate mixing, TRSP promotes a geometrically healthier transition operator without altering core attention. Experiments show significant improvements across general capabilities and long-context benchmarks. Notably, on NoLiMa at $8\times$ the training length, TRSP retains $83\%$ accuracy and surpasses the Differential Transformer and Gated Attention by approximately 30 and 50 percentage points, respectively. Code available at: https://github.com/Eziotao-tyd/TRSP.

cs.AI↗