Searcharxiv⌕ Search

arXiv subjects

Cong Chen

Publications and source records attributed to Cong Chen.

At least 19 recordsLinked to original sources
arXiv2026

Optimal Uniform Pricing for Multi-Interval Dispatch without Make-Whole Uplifts

In a network with ramp-limited generators and inaccurate net-demand forecasts, practical rolling-window dispatch can drive locational marginal prices (LMPs) below generators' bid-in offers. In such cases, out-of-market (OOM) settlements are used to compensate generators and maintain dispatch-following incentives, but OOM can have negative consequences, including nontransparent real-time price signals, discriminatory compensation, and incentives for untruthful bidding. This paper presents an optimal uniform pricing rule that minimizes demand payments, eliminates OOM make-whole payments, preserves LMP-based congestion charges, and ensures revenue adequacy. We derive the proposed pricing rule in closed form and relate it to existing pricing schemes. Numerical comparisons demonstrate favorable generator profits and reduced price volatility. However, higher generator profits are accompanied by increased demand payments, reflecting the in-market, uniform allocation of ramping costs while preserving the LMP-based congestion charges widely used in real-time market settlements. The numerical results also show that, under LMP with OOM settlement, a price-taking generator has an incentive to inflate its offer, whereas this incentive is absent under the proposed pricing rule within the tested bid range.

eess.SY↗
arXiv2026

Are Android GUI Agents Robust Against Runtime Anomalies? AnTrap: Evaluating Agents in Dynamic Adversarial Environments

GUI agents often encounter dynamic anomalies when deployed on Android devices, from unexpected pop-ups to action misuse, yet existing benchmarks lack systematic evaluation of agent robustness against runtime anomalies. We introduce AnTrap, a comprehensive benchmark that injects dynamic perturbations into agent execution trajectories. We propose a taxonomy organizing real-world anomalies into four layers (State, Thinking, Action and Round) with ten fine-grained subcategories, and develop a construction pipeline that preserves task solvability while introducing realistic adversarial conditions. Evaluating 16 leading GUI models, we reveal universal vulnerability to dynamic anomalies, with even the strongest models suffering significant performance degradation. Furthermore, we conduct GRPO training in both original and adversarial environments to validate our benchmark, separating environment-learnable anomalies from reasoning-bottlenecked ones. Our findings show that while single-step traps at state and action layers are largely addressable through adversarial reinforcement learning, deep contextual traps, like state deadlock, expose intrinsic limitations that cannot be resolved by training in environments with traps alone.

cs.AI↗
arXiv2026

Multi-Task Consistency-based Detection of Adversarial Attacks

Deep Neural Networks (DNNs) have found successful deployment in numerous vision perception systems. However, their susceptibility to adversarial attacks has prompted concerns regarding their practical applications, specifically in the context of autonomous driving. Existing defenses often suffer from cost inefficiency, rendering their deployment impractical for resource-constrained applications. In this work, we propose an efficient and effective adversarial attack detection scheme leveraging the multi-task perception within a complex vision system. Adversarial perturbations are detected by the inconsistencies between the inference outputs of multiple vision tasks, e.g., object detection and instance segmentation. To this end, we developed a consistency score metric to measure the inconsistency between vision tasks. Next, we designed an approach to select the best model pairs for detecting inconsistencies effectively. Finally, we evaluated our defense against PGD attacks across multiple vision models on the BDD100k validation dataset. The experimental results demonstrated that our defense achieved a ROC-AUC performance of 99.9% detection within the considered attacker model.

cs.CV↗
arXiv2026

Wave Scattering at temporal interfaces with spatial-translation-symmetry mismatch

Temporal interfaces enable wave manipulation through broken time-translation symmetry, but conventional formulations generally assume that spatial-translation symmetry is preserved across the interface. Here we consider temporal interfaces between periodic media with mismatched spatial symmetries. It is discovered that the reciprocal-lattice vectors of the pre- and post-switching media enter a generalized quasi-momentum-matching condition, giving rise to reciprocal-lattice-assisted wave-vector conversion. We then develop a multichannel temporal-scattering theory and validate it in one- and two-dimensional elastic lattices. A single incident Bloch mode can thereby excite multiple post-interface Bloch modes with distinct wave vectors and frequencies, a response inaccessible at conventional temporal interfaces. These results establish symmetry mismatch as a new degree of freedom for simultaneous control of wave vector and frequency in time-modulated periodic media.

physics.class-ph↗
arXiv2026

Can Large Language Models Execute Parent Orders?

Parent-order execution is a core problem in algorithmic trading, where the goal is to split a large order into smaller orders while reducing execution costs. Existing approaches either rely on pre-specified market assumptions that may not hold in practice, or require task-specific training that limits adaptability to new settings. To overcome these limitations, we present the first systematic study of large language models (LLMs) for parent-order execution. This extends the use of LLMs in finance from what to trade to how to execute. We propose PACE (Plan-Ahead Controlled Execution), a hierarchical framework that decomposes parent-order execution into long-horizon planning and short-horizon execution, requiring neither explicit market assumptions nor task-specific training. Experiments on Shenzhen Stock Exchange Level-1 data show that PACE outperforms TWAP, Almgren-Chriss, and learning-based baselines, exceeding the strongest baseline by 0.65 bps. Behavioral analysis reveals that LLMs make execution decisions differently from human investors: higher model confidence predicts better performance rather than worse returns, and the model trades earlier rather than procrastinating toward the deadline. These findings suggest that LLMs can complement human traders in execution decisions.

cs.CE↗
arXiv2026

Linking effective Ratner equidistribution to the semicircle law for skew-shift matrices

We consider large Hermitian matrices whose entries are defined by evaluating the exponential function along orbits of the skew-shift \(\frac{j(j-1)}{2}\omega + jy + x \mod 1\) for irrational \(\omega\). We establish a rigorous connection between the effective Ratner equidistribution theorem for unipotent orbits in \(\SL(3,\R)/\SL(3,\Z)\) and the global semicircle law for such deterministic matrices. For frequency sequences satisfying a Diophantine condition, we prove that the empirical spectral distribution of these matrices converges to the Wigner semicircle law with optimal polynomial rate \(O(N^{-1})\); for rectangular matrices the corresponding Marchenko--Pastur law is obtained. The proof uses a multi-parameter effective mixing property derived from the effective Ratner equidistribution theorem, combined with a graph-theoretic expansion of the moments. Our results evidence the quasirandom nature of the skew-shift dynamics observed in other contexts by Bourgain, Goldstein and Schlag, and Rudnick, Sarnak and Zaharescu, and provide a dynamical systems proof of the semicircle law with an improved convergence rate.

math.DS↗
arXiv2026

Ramping Procurement and Bid-Cost Recovery in Real-Time Market

We study ramping procurement co-optimized with economic dispatch under net-demand uncertainty. We examine two flexible ramp product designs implemented by grid operators: single-interval and multi-interval co-optimization. Both rely on rolling-window stochastic optimization with binding and advisory interval decisions. We develop analytical frameworks to evaluate generator profits, consumer payments, bid cost recovery (BCR), and operational efficiency. In particular, net-demand uncertainty may lead to generator under-compensation, requiring discriminatory BCR. While operational efficiency is invariant to energy and ramp prices, producer profits and consumer payments depend critically on pricing. We examine locational marginal pricing (LMP) and two uniform pricing: maximum dispatch cost pricing (MDCP) and maximum temporal locational marginal pricing (MTLMP). With out-of-market BCR, LMP yields discriminatory energy prices, whereas MDCP eliminates BCR and MTLMP does so in most cases. This property enables us to establish truthful bidding incentives for price-taking generators under MDCP. Our analysis highlights trade-offs between single- and multi-interval co-optimization and pricing designs: single-interval energy-ramp co-optimization is advantageous under high forecast uncertainty and moderate ramping requirements, whereas multi-interval co-optimization is superior when net-demand forecasts are relatively accurate and ramp needs are challenging. Empirical results on CAISO and ERCOT data show that MDCP and MTLMP increase producer profits with negligible BCR, albeit at the expense of higher consumer payments relative to LMP.

eess.SY↗
arXiv2026

Resonance-induced frequency splitting and evanescent modes at temporal interfaces in elastic metamaterials

Temporal interfaces, defined by abrupt changes in material properties, break temporal translational symmetry and enable wave phenomena fundamentally different from those at spatial interfaces. Unlike spatial scattering, temporal scattering preserves momentum rather than energy, leading to instantaneous frequency shifts governed by the dispersion relations on either side of the interface. Existing studies in elastic media have mainly considered non-resonant materials, and allow only one-to-one frequency conversion across temporal interfaces. Here, we propose temporal interfaces formed by the sudden activation of local resonators in elastic metamaterials, which induces a transition from non-resonant to resonant dispersion. We demonstrate that such interfaces can induce frequency splitting among scattered waves and elucidate how the scattered-wave amplitudes are governed by the weighted modal correlation coefficients and impedances. Moreover, a novel temporal evanescent mode, characterized by spatial stationarity and temporal decay is demonstrated after the interface, which is well explained by the negative effective modulus evaluated at imaginary frequencies. These findings establish a foundational understanding of wave dynamics at temporal interfaces involving resonant materials, open new opportunities for wave manipulation in time-varying solids.

physics.app-ph↗
arXiv2026

CAPE: Contrastive Action-conditioned Parallel Encoding for Embodied Planning

Embodied agents need to predict the future consequences of candidate actions in order to plan effectively before execution. Existing visual dynamics models learn by reconstructing future visual states or rolling out dense latent representations, which spreads learning capacity across visually salient but planning-irrelevant content rather than the action-conditioned changes that drive manipulation outcomes. We propose CAPE, a Contrastive Action-conditioned Parallel Encoding framework that learns visual dynamics by distinguishing the future outcomes induced by different action sequences. Given an initial observation and a candidate action sequence, CAPE decodes the full future latent trajectory in a single forward pass and is trained with a Goal-Convergent Contrastive Objective that aligns predictions corresponding to the same future outcome while separating those corresponding to different outcomes. On real-world DROID and zero-shot transfer to RoboCasa, CAPE substantially outperforms prior baselines on future-state retrieval, offline action matching, and closed-loop planning, while notably reducing planning-time inference cost at long prediction horizons.

cs.RO↗
arXiv2026

MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism

Current Vision-Language Models struggle with hours-long videos because processing full-length visual sequences induces prohibitive token explosion and attention dilution. To overcome this, we introduce MemDreamer to decouple perception and reasoning, shifting long-video understanding into an agentic exploration process. As a plug-and-play framework, it incrementally streams videos to construct a Hierarchical Graph Memory, a top-down three-tier architecture for semantic abstraction, anchored by a foundational graph capturing spatiotemporal and causal relations. During inference, the reasoning model employs agentic tool-augmented retrieval, navigating hierarchies, searching nodes, and traversing logical edges via an Observation-Reason-Action loop. Experiments show MemDreamer achieves SOTA results across four mainstream benchmarks, narrowing the gap with human experts to only 3.7 points. It constrains the reasoning context window to merely 2% of full-context ingestion while delivering a 12.5 point absolute accuracy gain. Furthermore, statistical analysis uncovers a strong positive linear correlation between an VLM's performance on logic reasoning and long-video understanding benchmarks, establishing agentic capability scaling as a new paradigm for multimodal comprehension.

cs.CV↗
arXiv2026

Streaming Communication in Multi-Agent Reasoning

Multi-agent reasoning systems adopt a "generate-then-transfer" paradigm that forces end-to-end latency to scale linearly with pipeline depth. We introduce StreamMA, a multi-agent reasoning system that streams each reasoning step to downstream agents as soon as it is generated, pipelining adjacent agents and thus reducing latency. Surprisingly, this pipelining also improves effectiveness: because multi-step reasoning quality is non-uniform and early steps are more reliable than later ones, working with these reliable early steps instead of the full chain prevents error-prone late steps from misleading downstream agents. We formalize both advantages with the first closed-form joint analysis of stream, serial, and single protocols, deriving the effectiveness ordering, speedup upper bound, and cost ratio. Across eight reasoning benchmarks spanning mathematics, science, and code, two frontier LLMs (Claude Opus 4.6 and GPT-5.4), and three topologies (Chain, Tree, Graph), StreamMA outperforms both baselines (avg. +7.3 pp, max +22.4 pp on HMMT 2026; Claude Opus 4.6-high). Beyond these contributions, we discover a "step-level scaling law": increasing per-agent steps consistently improves both effectiveness and efficiency, a new scaling dimension orthogonal to and composable with agent-count scaling.

cs.CL↗
arXiv2026

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching

Wide-baseline matching (WBM) requires integrating geometric understanding, viewpoint changes, fine-grained perception, and occlusion reasoning, making it a challenging testbed for spatial reasoning in multimodal large language models (MLLMs) deployed in physical environments. However, current MLLMs lack systematic evaluation and training frameworks for these capabilities. We introduce ReasonMatch-Bench, a benchmark stratified by viewpoint displacement and matching granularity across indoor, outdoor, and object-centric scenarios, and show that current MLLMs still struggle with fine-grained wide-baseline correspondence: on a difficult 90-sample subset, human annotators achieve 84.0 F1, while the best existing baseline reaches 37.2. To bridge this gap, we build a scalable data-generation pipeline that automatically extracts wide-baseline view pairs from large-scale video-3D corpora, including RGB-D videos and SfM reconstructions, yielding diverse and verifiable supervision. We further propose Dynamic Correspondence Reinforcement Learning (DCRL), which combines Image-Level Viewpoint Progression and Point-Level Correspondence Curriculum to improve WBM training through verifiable rewards without explicit CoT supervision. Extensive experiments show that DCRL substantially improves ReasonMatch-Bench and transfers to related spatial benchmarks, while maintaining general visual understanding performance with modest gains on several benchmarks.

cs.CV↗
arXiv2026

A Scalable Bundle Method for Exact Reformulation of SDP in Three-Phase Power Flow Feasibility

Power flow feasibility assessment is computationally challenging for unbalanced three-phase distribution networks. This paper develops a vectorized semidefinite program (SDP) based on the bus injection model (BIM) and reformulates its dual as an exact-penalty problem, enabling us to develop a scalable three-cut proximal bundle method for feasibility assessment. The proposed bundle method is numerically over 400 times faster than MOSEK with less than 1/2000 of its memory; on the decomposed BIM-SDP, approximately 2 times faster with 75% less memory.

math.OC↗
arXiv2026

The Great Pretender: A Stochasticity Problem in LLM Jailbreak

"Oh-Oh, yes, I'm the great pretender. Pretending that I'm doing well. My need is such, I pretend too much..." summarizes the state in the area of jailbreak creation and evaluation. You find this method to generate adversarial attacks proposed by a reputable institution (e.g., BoN from Anthropic or Crescendo from Microsoft Research). However, this method does not deliver on the promise claimed in the paper despite having top ASR scores against industry-grade LLMs. You successfully generate the jailbreak prompts against your target (open) model. However, the generated jailbreak prompt works against the target model with a 50% consecutive success rate (5 out of 10 attempts) despite having an 80% ASR (on paper) on the latest closed-source model (with a guardrail system)! This observation leads us to think. First, Attack Success Rate (ASR), the primary metric for LLM jailbreak benchmarking, is not a stable quantity. Second, published ASR numbers are therefore systematically inflated and incomparable across papers. Therefore, we wonder "Why a successful jailbreak prompt does not perform consistently well against a target model on which the prompts have been optimized?". To answer this question, we study the impact of stochasticity not only during attack evaluation but also during attack generation. Our evaluation includes several jailbreak attacks, models (different sizes and providers), and judges. In addition, we propose a new metric and two new frameworks (CAS-eval and CAS-gen). Our evaluation framework, CAS-eval, shows that an attack can have an ASR drop of up to 30 percentage points when a jailbreak prompt needs to succeed on more than one attempt. Thankfully, our attack generation framework (CAS-gen) improves previous jailbreak methods and helps them recover this loss of 30 percentage points!

cs.CR↗
arXiv2026

Reachable-Set Decomposition for Real-Time Aggregation of Multi-Zone HVAC Fleets

Aggregating building heating, ventilation, and air-conditioning (HVAC) fleets provides substantial real-time flexibility to power system operations. However, real-time aggregation of multi-zone HVAC fleets faces two key challenges: (i) strong coupling across zones and time makes flexibility characterization high-dimensional and computationally demanding, and (ii) the sequential revelation of temperature states and exogenous conditions requires that decisions made at each period preserve feasibility over the remaining horizon using only currently realized information. To address these challenges, this paper proposes a reachable-set decomposition framework comprising an offline decomposition stage and a real-time policy. In the offline stage, backward reachable sets are formulated to encode remaining-horizon feasibility into per-period state constraints, so that any state within the current reachable set is guaranteed to sustain feasible operation over the entire remaining horizon. A tailored inner approximation is then developed for tractable calculation in multi-zone-coupled HVAC settings. In the real-time stage, aggregate flexibility is computed efficiently via building-level parallel linear programs followed by closed-form Minkowski summation of power intervals, and any regulation signal within the reported flexibility interval admits a recursively feasible disaggregation. Case studies demonstrate the effectiveness of the proposed framework in aggregate flexibility characterization, disaggregation feasibility, and scalable computation.

eess.SY↗
arXiv2026

Risk-Aware Allocation of Transmission Capacity for AI Data Centers

Rapid growth in AI-driven data center loads is creating significant challenges for transmission grid interconnection. This paper proposes robust and risk-aware frameworks to quantify transmission capacity as firm and flexible capacities. We efficiently solve the robust optimization problem to determine firm capacity when minimizing unserved data center demand. Building upon this, we introduce a risk-aware allocation for flexible capacity, showing that tolerating a minimal probability of service interruption and blackout can unlock substantial flexible capacity of transmission networks and accelerate data center interconnection. To efficiently allocate scarce transmission capacities among competing data centers, we adopt the simultaneous ascending auction, characterizing products by capacity, risk level, and location. Under additive or symmetric concave valuation functions, the auction converges to a competitive equilibrium and achieves efficient allocation.

eess.SY↗
arXiv2026

Android Coach: Improve Online Agentic Training Efficiency with Single State Multiple Actions

Online reinforcement learning (RL) serves as an effective method for enhancing the capabilities of Android agents. However, guiding agents to learn through online interaction is prohibitively expensive due to the high latency of emulators and the sample inefficiency of existing RL algorithms. We identify a fundamental limitation in current approaches: the Single State Single Action paradigm, which updates the policy with one-to-one state-action pairs from online one-way rollouts without fully exploring each costly emulator state. In this paper, we propose Android Coach, a novel framework that shifts the training paradigm to Single State Multiple Actions, allowing the agent to sample and utilize multiple actions for a single online state. We enable this without additional emulator overhead by learning a critic that estimates action values. To ensure the critic serves as a reliable coach, we integrate a process reward model and introduce a group-wise advantage estimator based on the averaged critic outputs. Extensive experiments demonstrate the effectiveness and efficiency of Android Coach: it achieves 7.5% and 8.3% success rate improvements on AndroidLab and AndroidWorld over UI-TARS-1.5-7B, and attains 1.4x higher training efficiency than Single State Single Action methods PPO and GRPO at matched success rates.

cs.LG↗
arXiv2026

TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders

We propose TC-AE, a ViT-based architecture for deep compression autoencoders. Existing methods commonly increase the channel number of latent representations to maintain reconstruction quality under high compression ratios. However, this strategy often leads to latent representation collapse, which degrades generative performance. Instead of relying on increasingly complex architectures or multi-stage training schemes, TC-AE addresses this challenge from the perspective of the token space, the key bridge between pixels and image latents, through two complementary innovations: Firstly, we study token number scaling by adjusting the patch size in ViT under a fixed latent budget, and identify aggressive token-to-latent compression as the key factor that limits effective scaling. To address this issue, we decompose token-to-latent compression into two stages, reducing structural information loss and enabling effective token number scaling for generation. Secondly, to further mitigate latent representation collapse, we enhance the semantic structure of image tokens via joint self-supervised training, leading to more generative-friendly latents. With these designs, TC-AE achieves substantially improved reconstruction and generative performance under deep compression. We hope our research will advance ViT-based tokenizer for visual generation.

cs.CV↗