arXiv subjects

Qian Zhang

Publications and source records attributed to Qian Zhang.

At least 19 recordsLinked to original sources

arXiv2026

Anchor3R: Streaming 3D Reconstruction with Transient Anchors for Long-Horizon Visual Mapping

Long-horizon online visual mapping requires continuous camera-motion and scene-geometry estimation under bounded computation. Recent feed-forward 3D reconstruction models provide strong geometric priors, but streaming variants often predict poses in a fixed or historically maintained coordinate system, leading to train--test mismatch, early-anchor attention bias, and accumulated drift. We propose \emph{Anchor3R}, a current-centric streaming 3D reconstruction framework that predicts window-relative poses and local geometry in the current-frame coordinate system. Overlapping predictions form a dense relative-pose graph, supporting online pose updates and loop-aware motion averaging for global reconstruction. Experiments on indoor, outdoor, driving, and RGB-D benchmarks demonstrate improved long-horizon pose accuracy and dense reconstruction quality over existing streaming baselines. Despite being trained only on 48-frame sequences, Anchor3R directly generalizes to streams exceeding 10,000 frames while maintaining bounded GPU memory during online inference. Code is available at https://github.com/polar-explorer/Anchor3R.

cs.CV↗

arXiv2026

REAL-Q: E2E LLM Quantization via Dynamic Gradient Descent

Post-training quantization (PTQ) is essential for deploying large language models (LLMs) under strict resource constraints. State-of-the-art PTQ methods quantize each layer with a single closed-form second-order solver: to remain analytically tractable, they heavily approximate the global loss (dropping cross-channel coupling, pooling output rows into groups), and they then freeze the resulting Hessian across the entire layer, with no way to refresh it as the loss landscape shifts column by column--a phenomenon we call information misalignment. We propose REAL-Q (Real-time E2E-loss Aligned LLM Quantization), a novel PTQ paradigm that breaks this compromise: instead of diluting the objective for the sake of analytic tractability, REAL-Q targets an end-to-end-aligned surrogate of the global loss and refines it via fine-grained, dynamic Block-wise Gradient Descent applied after every column block (128 columns). By coupling this fine-grained correction with a sliding window mechanism for smooth cross-layer transitions, REAL-Q effectively mitigates error propagation across the network. On LLaMA-3.1 (8B and 70B) and Qwen3 (0.6B-32B) at W4A16, REAL-Q reduces end-to-end KL divergence by up to ~49% relative to state-of-the-art globally-guided methods.

cs.LG↗

arXiv2026

Generative AI for Analysts

We study how generative artificial intelligence (GenAI) reshapes financial analysts' information production. Using the 2023 integration of GenAI into FACTSET as a plausibly exogenous change in AI access, we find that FACTSET-associated reports become markedly richer--featuring 26% more distinct information sources, 24% broader topical coverage, and 21% more analytical methods--while also improving timeliness. However, these gains do not uniformly improve decision quality: relative forecast accuracy declines when analysts face greater information-processing demands. Yet, a machine-learning benchmark processing the same observable inputs shows no analogous deterioration, pointing to a human processing constraint rather than poorer underlying information. Placebo tests using other data vendors make a common platform-wide technology trend unlikely. Overall, GenAI relaxes information-acquisition constraints while making human attention a more important bottleneck.

q-fin.ST↗

arXiv2026

Anchored, Not Graded: Vision-Language Models Fail at Slant-from-Texture Perception

Human perception of surface slant from texture exhibits systematic, graded biases that emerge reliably in psychophysical experiments. Prior work showed that unsupervised CNNs reproduce several human-like biases, while supervised CNNs do not. Do Vision-Language Models (VLMs) exhibit similar competences? Across multiple VLM families and model scales, zero-shot and in-context prompting both produce distinctive failures: slant is predicted at only a small set of anchors (e.g., 0\degree, $\pm$25\degree, $\pm$45\degree) with little dependence on stimulus field of view, optical slant, or surface curvature. Supervised fine-tuning partially remediates the failure, but residual anchoring persists. While success in high-level vision-language benchmarks might not require sensitivity to low-level geometric cues, we interpret anchoring as a failure at the representation-to-output language interface: not necessarily an absence of geometric encoding, but a failure to express it in a graded form.

cs.CV↗

arXiv2026

Line-Coupled Language Model

Autoregressive language models generate one token per decoding step, limiting the useful output of each forward pass. Although diffusion models, insertion-based decoding, and multi-token prediction enable parallel generation, they either incur additional training-time token traffic or struggle to predict strongly dependent future tokens. We introduce the Line-Coupled Language Model (LCLM), an autoregressive model that advances multiple text lines together by predicting the next token for every active line while coupling the lines through shared causal context. LCLM interleaves line tokens into a single causal sequence and uses line-staggered rotary positions, retaining the standard next-token objective and causal attention. Controlled experiments show that cross-line targets are substantially less dependent than consecutive same-line targets, supporting lines as parallel generation units. With 881M parameters, LCLM produces an average of 2.94 content tokens per forward pass with a validation cross-entropy loss of 2.44, compared with 1.00 token per forward pass and a loss of 2.39 for the vanilla autoregressive baseline. Most notably, even when LCLM generates 16 tokens per forward pass, its loss is only 0.09 higher than that of the vanilla autoregressive baseline (2.34 vs. 2.25).

cs.CL↗

arXiv2026

AccidentSim: Generating Vehicle Collision Videos with Physically Realistic Collision Trajectories from Real-World Accident Reports

Collecting real-world vehicle accident videos for autonomous driving research is challenging due to their rarity and complexity. While existing driving video generation methods may produce visually realistic videos, they often fail to deliver physically realistic simulations because they lack the capability to generate accurate post-collision trajectories. In this paper, we introduce AccidentSim, a novel framework that generates physically realistic vehicle collision videos by extracting and utilizing the physical clues and contextual information available in real-world vehicle accident reports. Specifically, AccidentSim leverages a reliable physical simulator to replicate post-collision vehicle trajectories from the physical and contextual information in the accident reports and to build a vehicle collision trajectory dataset. This dataset is then used to fine-tune a language model, enabling it to respond to user prompts and predict physically consistent post-collision trajectories across various driving scenarios based on user descriptions. Finally, we employ Neural Radiance Fields (NeRF) to render high-quality backgrounds, merging them with the foreground vehicles that exhibit physically realistic trajectories to generate vehicle collision videos. Experimental results demonstrate that the videos produced by AccidentSim excel in both visual and physical authenticity.

cs.CV↗

arXiv2026

Locational Marginal Pricing for Adaptive Robust Look-Ahead Dispatch with Casual Affine Recourse

This paper develops a marginal pricing mechanism for adaptive robust look-ahead economic dispatch (LAED) under net-load uncertainty. In current market practice, deterministic multi-interval dispatch can misprice flexibility when forecast error is large. Fully adaptive robust (FAR) dispatch captures this uncertainty, but competing worst-case trajectories can imply different marginal values of demand, leaving no single price for market settlement. We propose causal affine recourse (CAR) as a tractable, price-forming approximation. CAR replaces independently optimized trajectory-specific schedules with a causal affine response policy, yielding a market-clearing model that retains the standard energy and congestion decomposition of DC Locational Marginal Pricing. We then demonstrate that CAR-LMP together with a ramp-adjusted current settlement supports dispatch-following and eliminates current-period lost opportunity costs. We solve the CAR problem by deriving a robust counterpart and present computational evidence on exact small DC instances, a ten-generator system, and an IEEE 300-bus public-network case. These simulations show that the proposed prices collapse exactly to deterministic LAED-LMP when robustness is inactive, remain stable in loose-ramp regimes, and produce economically meaningful price shifts when flexibility is scarce. The proposed pricing mechanism provides a practical bridge between adaptive robust dispatch and market-based pricing.

eess.SY↗

arXiv2026

Hierarchical Beam Training and Codebook Design for Movable Antenna-Assisted Near-Field Systems

As sixth-generation (6G) communication systems evolve toward higher frequency bands and larger array apertures, the near-field range expands rapidly, making near-field channel estimation increasingly important and challenging. Beam training has been recognized as an effective approach for channel state information (CSI) acquisition. However, because of the propagation characteristics of spherical waves, beam training needs to perform a joint search in the angle and distance domains, which results in unaffordable beam training overhead. By flexibly reconfiguring antenna positions, movable antenna (MA) technology can fully exploit the spatial variations of wireless channels and achieve more accurate beam focusing, thereby providing additional flexibility for efficient beam training design. Therefore, based on MA-assisted near-field systems, we develop a hierarchical beam training strategy that combines reduced training overhead with high beam gain and design a corresponding hierarchical codebook. This codebook forms focused beams over the joint angle-distance domain, maximizing beam gain within the target region while suppressing energy leakage into non-target regions. Simulation results confirm substantial performance gains of the method over the conventional fixed-position antenna (FPA) system and the far-field beam training method.

cs.IT↗

arXiv2026

VirSqueezer: Generating Realistic Deformations and Squeezing Dynamics in VR from Fine-Grained Squeezing Controls

Squeezing is one of the most natural forms of hand manipulation, inherently involving fine-grained, temporally evolving, per-finger flexion. In VR content creation, squeezing plays a unique role in enabling particular visual effects such as localized deformations and dynamic behaviors, e.g., bursting a Coke can or juicing a fruit, thereby expanding the expressive possibilities of VR content. However, existing techniques, such as 3D Gaussian splatting-based methods and diffusion-based video generation models, are limited in their ability to simulate fine-grained virtual squeezing effects. We introduce VirSqueezer, a framework designed to generate both localized deformations (primary effects) and complex squeezing dynamics, such as rupture and overflow (secondary effects). VirSqueezer captures squeezing control signals using a SenseGlove and provides the user with inferred resistance force feedback during the squeezing process. By estimating object contact areas, inferring physical properties, and simulating physical responses, VirSqueezer computes conditions that guide generation models for visual effect generation, ensuring both visual coherence and temporal synchronization with the simulation. Consequently, VirSqueezer enables the generation of physically realistic visual effects directly from continuous, fine-grained squeezing control signals. Our extensive evaluation demonstrates VirSqueezer's ability to reproduce realistic localized deformations, generate convincing visual dynamics, and maintain consistency in fine-grained squeezing controls.

cs.HC↗

arXiv2026

ForesightSafety-SAGE:A Fully Automated Scenario Generation and Safety Evaluation Framework for LLM Agents

Large language models (LLMs) are increasingly evolving from simple text-based interaction systems into LLM agents that can maintain memory, use tools, access external environments, and execute tasks. As their capabilities and autonomy expand, the safety risks they face also become more diverse. Existing evaluations often rely on manually written scenarios, static prompts, or final-output judgments, making it difficult to capture the diverse risks that agents may face during task execution. We introduce ForesightSafety-SAGE, a fully automated scenario generation and safety evaluation framework for LLM agents. Based on five risk dimensions,we instantiae abstract and diverse safety risks in real-world task execution into 1,072 measurable evaluation scenarios. Using the automated evaluation pipeline, 12 LLM agents are evaluated under two authority contexts. The results show that current agents still face substantial behavioral safety risks during task execution, with an average ASR of 47.1% and several models exceeding 70%. These findings demonstrate the importance of executable, process-level evaluation for understanding and improving LLM agent safety.

cs.AI↗

arXiv2026

RestoreBench: Can AI Agents Restore Power Flow Convergence?

Large Language Model (LLM) agents increasingly automate multi-step engineering workflows through tool use, interpretation of intermediate results, and iterative planning. Diagnosing and resolving non-convergent power flow cases is a promising yet largely unexplored application, as it requires engineering judgment, experimentation, and decision-making within constrained action spaces. We introduce a benchmark that evaluates these capabilities across multiple LLMs and three architectures: \emph{chatbot}, \emph{single agent}, and \emph{multi-agent} systems. The evaluation covers two power grids and 46 cases per grid, each requiring one or more corrective actions to restore convergence. The benchmark defines the simulation environment, observation and action spaces, and evaluation metrics, providing a reproducible foundation for developing agentic AI systems for power system planning and operation. The code is available at https://github.com/Mansutti081/RestoreBench

cs.AI↗

arXiv2026

Save 2050: A Planetary-Scale Collective Prediction System for the Singularity Crisis

The Anthropocene mode of development is driving civilization toward a "singularity crisis": artificial intelligence (AI) is rapidly approaching general intelligence (AGI) with escalating risks of losing control, while unrestrained economic growth generates super-exponential growth of entropy production that pushes the Earth system toward its tipping points. This paper proposes the "Save 2050" initiative: a distributed planetary-scale collective prediction system that aggregates judgments about the future from humans and AI through open registration, crowdsourcing, and incentive mechanisms, and integrates them via large-scale simulation into inspectable "predicted worlds," enabling humanity to systematically \emph{see} the future for the first time. We argue for the initiative's feasibility along four dimensions---the maturation of AI forecasting, human collective intelligence and the institutional environment, supporting progress in related fields, and societal demand. We then identify three key enabling technologies: long-horizon automated resolution, simulation-based prediction aggregation, and reflexivity governance. We analyze potential risks---including reflexivity, cognitive monoculture, narrative capture, and regulatory and ethical concerns---together with mitigation strategies, and we outline a phased roadmap with open problems. The initiative's primary goal is not to intervene in the future, but to make the future visible, discussable, and co-writable.

physics.soc-ph↗

arXiv2026

Faithful Evaluation of Semantic-ID Tokenizers for Generative Recommendation

Generative recommendation based on Semantic IDs (SIDs) represents each item as a discrete sequence of SIDs and is conventionally evaluated by matching the generated SID sequence against the target item's SID sequence. This evaluation is faithful only when each SID sequence uniquely identifies one item. In practice, SID collisions violate this condition: across the evaluated SID tokenizers and datasets, collision rates reach 30.52%, and SID-level Hit@10 is inflated by up to 103.36% relative to item-level Hit@10. To address this evaluation gap, we introduce Collision-Corrected Evaluation (CCE), which defines collision-aware item-level metrics (ItemHit@K, ItemNDCG@K) computed from generated SID sequences, and Zero-Collision Reassignment (ZCR), which constructs zero-collision SID assignments for existing tokenizers via minimum-cost reassignment. Applying these methods to four datasets and five representative SID tokenizers, we find that metric inflation scales with collision rate and is large enough to flip pairwise tokenizer comparisons under item-level re-evaluation. This finding calls into question the reliability of SID-level rankings reported in prior work and indicates that faithful tokenizer evaluation requires item-level correction or zero-collision SID assignments.

cs.IR↗

arXiv2026

Joint Beamforming and Phase Shifts Design for RIS-Enabled RSMA-ISAC Systems

This paper investigates the sensing-centric design of reconfigurable intelligent surface (RIS)-enabled rate-splitting multiple access-integrated sensing and communication (RSMA-ISAC) systems. Specifically, we propose a new beam-gain approximation method to enhance the sensing beam gain while satisfying communication quality-of-service (QoS) constraints.Since the joint optimization of the beamforming vectors and RIS phase shifts is highly coupled and non-convex, existing methods typically rely on generic optimization solvers involving substantial computational complexity. To address this issue, we propose an efficient constraints-separation-based alternating optimization algorithm (CS-AO). Our proposed algorithm effectively decouples the optimization variables and yields closed-form solutions for all subproblems, thereby significantly reducing the computational burden. Simulation results show that the proposed algorithm achieves sensing beam-gain performance comparable to successive convex approximation (SCA) and semidefinite relaxation (SDR) benchmarks, while achieving more than 120-fold and 50-fold runtime reductions. In addition, compared with conventional space-division multiple access (SDMA) schemes, the proposed design exhibits substantial sensing beam gain.

cs.IT↗

arXiv2026

Joint Power Allocation and Phase-Shift Design for Beyond-Diagonal Stacked Intelligent Metasurfaces-Aided ISAC Systems

Stacked intelligent metasurfaces (SIM) provide an efficient architecture for integrated sensing and communication (ISAC) with few radio-frequency (RF) chains. However, diagonal SIM provide only element-wise phase control, so balancing multiuser communication and sensing performance may require additional layers. In this letter, we propose a beyond-diagonal SIM (BD-SIM) architecture for ISAC, enabling controllable intra-layer coupling through reconfigurable impedance networks, thereby enhancing wave-domain processing flexibility. We develop a unified alternating optimization framework applicable to fully-connected, group-connected, and diagonal SIM architectures. Within this framework, we derive a closed-form power allocation rule and propose an effective variable separation algorithm for multi-layer phase-shift design. Simulation results show that the proposed BD-SIM achieve a better communication-sensing trade-off and require fewer layers to attain performance comparable to conventional SIM.

cs.IT↗

arXiv2026

Synthesis and stability of high-$T_c$ LaH$_{10\pmδ}$ films at high pressures

High-pressure hydrides hold the record for the highest superconducting critical temperatures across all classes of superconductors. Currently lanthanum decahydride, LaH$_{10}$, exhibits the highest critical temperature among binaries, with $T_c \approx$ 250 K at pressures between 140-180 GPa. Here, we report the synthesis of LaH$_{10\pmδ}$ films in two DACs at pressures of 168 GPa and 176 GPa via in situ laser heating of elemental lanthanum films with ammonia borane (NH$_3$BH$_3$) as the hydrogen donor. The high-symmetry fcc lanthanum sublattice (space group $Fm\bar3m$) is resolved using synchrotron X-ray diffraction, with unit cell parameters in excellent agreement with previous studies on bulk samples. We provide confirmation of high-$T_c$ superconductivity in LaH$_{10\pmδ}$ with highest $T_c$ of 247 K at 176 GPa evidenced in electrical measurements. The characteristic suppression of superconductivity is observed in magnetic fields. Furthermore, combined diffraction and electrical measurements reveal remarkable temporal stability of both the crystal structure and the high-$T_c$ superconductivity over the full measurement period of about 300 days post laser heating. Our work establishes film precursors using physical vapour deposition (PVD) techniques as a practical route to hydride formation, opening a pathway toward the controlled synthesis of promising ternary hydrides and the integration of micro-fabricated device geometries in diamond anvil cells.

cond-mat.supr-con↗

arXiv2026

Properties and applications of Lorentz--Muckenhoupt classes

In this paper, through the introduction of Lorentz--Muckenhoupt classes, we systematically investigate the boundedness of maximal operators on multiplier weighted Lorentz spaces. As applications, we give the characterization of the commutators of fractional integrals, which yields a partial answer to an open question proposed by D. Cruz-Uribe. Second, Hardy inequalities in Lorentz spaces are established, with the critical case $p=d$, in which the classical Hardy inequality fails. Finally, we apply the Lorentz estimates to fractional Schrödinger equations with singular potentials.

math.CA↗

arXiv2026

DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT

Recent successes in autoregressive (AR) generation models, such as the GPT series in natural language processing, have motivated efforts to replicate this success in visual tasks. Some works attempt to extend this approach to autonomous driving by building video-based world models capable of generating realistic future video sequences and predicting ego states. However, prior works tend to produce unsatisfactory results, as the classic GPT framework is designed to handle 1D contextual information, such as text, and lacks the inherent ability to model the spatial and temporal dynamics essential for video generation. In this paper, we present DrivingWorld, a GPT-style world model for autonomous driving, featuring several spatial-temporal fusion mechanisms. This design enables effective modeling of both spatial and temporal dynamics, facilitating high-fidelity, long-duration video generation. Specifically, we propose a next-state prediction strategy to model temporal coherence between consecutive frames and apply a next-token prediction strategy to capture spatial information within each frame. To further enhance generalization ability, we propose a novel masking strategy and reweighting strategy for token prediction to mitigate long-term drifting issues and enable precise control. Our work demonstrates the ability to produce high-fidelity and consistent video clips of over 40 seconds in duration, which is over 2 times longer than state-of-the-art driving world models. Experiments show that, in contrast to prior works, our method achieves superior visual quality and significantly more accurate controllable future video generation. Our code is available at https://github.com/YvanYin/DrivingWorld.

cs.CV↗