Search arXiv⌕ Search

arXiv subjects

Chen Wang

Publications and source records attributed to Chen Wang.

At least 37 records · Page 2Linked to original sources
arXiv2026

How to Build a Benchmark That Actually Measures Taste

Expert-aligned "taste" benchmarks should reward craft judgment, not the ability to game the test. We introduce TasteBench, a pairwise good-vs-bad benchmark across visual, brand, book, and tech items under a frozen rubric with expert-only gold (panel n>=3; percent agreement >=0.60 primary gate; weak engagement labels train/analysis-only), together with a control protocol that separates craft judgment from test-gaming. Applying the protocol to a Round-1 pilot (primary_human_expert; three biological human experts; n=250 pairs) surfaces and quantifies three validity threats: two construction artifacts that inflate the trivial-baseline layer, and a difficulty ceiling that inflates every score. (1) Position: the preferred item is slot A with probability 0.956, so an always_item_a policy scores 0.956 (fair chance 0.5). (2) Lexical leakage: a filename token cue scores 0.912. (3) Difficulty ceiling: craft domains show near-ceiling human agreement (book/brand/tech 1.0), and even under A/B randomization (eval_assignment_seed7; gold_side_A ~0.47) all five VLM cards reach 1.0 on craft, with only visual separating (~0.84-0.91; a post-hoc hard subset, n=107, leaves craft at 1.0). The protocol (expert-only gold, a weak-label firewall, side randomization at construction, filename scrubbing, and hard filters) makes each artifact measurable and, for the two construction artifacts, correctable; we release a reference eval harness and a side-randomization tool, and show the tool removes the position skew (0.916 to 0.495/0.505). The result is a calibrated view of what the benchmark does and does not yet measure: position and leakage are fixable, whereas the craft-domain ceiling is a pair-difficulty limit that Round-2 must address. We do not evaluate engagement, era/circle conditioning, or calibration here, and we claim no general taste SOTA.

cs.AI↗
arXiv2026

How Should a Camera-First AI Agent Work?

Camera-first agents must act on the visual world as it unfolds. We argue that the central obstacle for future camera-first agents is not recognition ability - multimodal models (vision-language and live/streaming alike) generalize well through language and remain the right tool for semantic reasoning - but time. Many visual targets are ephemeral: they appear, are query-relevant, and leave within a short window. Binding memory to the same end-to-end path as reasoning means that by the time a monolithic pipeline completes, the evidence is gone. We formalize this as Ephemeral-Target Interaction (ETI) and a Perceptual Deadline Contract separating a hard memory deadline from a soft reasoning deadline, grounded in the bounded, passive nature of sensory and working memory. We propose a two-deadline architecture: an always-on, bounded, non-semantic fast path; an active remembering mechanism that commits a moment to durable memory before it is overwritten (event-driven in v1); and a deferred deliberation layer (multimodal model + tools). We instantiate the contract on real MOT17 track windows, a consistency check, and calibrate the single-path baseline from measured frontier-model latency: even a short answer takes 1.2-9.3 s, and an agentic identify-and-search longer. Answers can be late; evidence cannot be missed.

cs.AI↗
arXiv2026

TrimSO(2): Fast and Memory-Efficient Training of Equivariant Interatomic Potentials

Equivariant interatomic potentials enable accurate and efficient simulations of molecules and materials. Among them, models based on SO(2) convolutions reduce the cost of tensor products and achieve state-of-the-art accuracy, but their training remains time-consuming and memory-intensive. Existing training implementations materialize large edge tensors for representation transformations surrounding dense matrix multiplications, increasing memory usage and data movement. We observe that these transformations can be integrated into the model's existing dataflow, avoiding separate intermediate materialization. We introduce TrimSO(2), a fast and memory-efficient algorithm for SO(2)-based equivariant models. It realizes this principle through rotation on gather, recombination with activation, and inverse rotation on reduction, with support for the higher-order differentiation required for training. By avoiding intermediate materialization, TrimSO(2) delivers 2.71-16.73$\times$ operator speedups across forward, backward, and double backward and reduces model-level high-bandwidth memory traffic by 3.81-9.88$\times$. Finally, TrimSO(2) achieves 2.07-2.94$\times$ training speedups and 1.53-3.16$\times$ reductions in peak training memory over PyTorch implementations for official eSEN, UMA, and EquiformerV3 workloads on A100 and H100 GPUs.

cs.DC↗
arXiv2026

LunaTP: Enabling Efficient and Scalable Tensor Product for Equivariant MLIPs

Equivariant machine learning interatomic potentials (MLIPs) promise atomistic simulations with accuracy approaching that of quantum-mechanical calculations. However, the high computational cost of their core Clebsch--Gordan tensor product (CGTP) convolutions severely limits model scalability and efficiency. In this paper, we rethink the parallel execution of CGTP convolutions and introduce LunaTP. Built on node-centric execution, LunaTP exploits path-group parallelism and multi-level reuse to accelerate CGTP convolutions and higher-order derivative computation while preserving the underlying mathematical formulation. On an NVIDIA H100 GPU, LunaTP achieves kernel speedups of up to 250.0$\times$ over e3nn and 17.1$\times$ over OpenEquivariance. It also delivers end-to-end training throughput gains of up to 28.7$\times$ over e3nn and 3.11$\times$ over OpenEquivariance. Finally, LunaTP demonstrates scalability and robust performance across models, workload scales, and GPUs, delivering substantial acceleration for training and atomistic simulation with high-accuracy equivariant MLIPs.

cs.DC↗
arXiv2026

CIRRA: Dual-Level Continual Instruction Reconciliation with Ongoing Execution for Embodied Robot Agents in Interactive Household Tasks

Household robots must accommodate new user instructions while executing ongoing tasks. Existing agents often regenerate or extensively revise the remaining task sequence, introducing plan ambiguity, logical inconsistency, and redundant execution. We formulate continual instruction reconciliation and propose CIRRA (Continual Instruction Reconciliation for Robot Agents), a dual-level framework combining LLM-based semantic reasoning with rule-constrained structural integration. CIRRA first grounds incoming instructions to unique executable skills and resolves underspecified actions and execution locations. It then preserves the ongoing subtask sequence as an execution backbone and generates integration candidates by inserting incoming subtasks into location-matched segments. The semantic reasoner evaluates only modified segments to identify dependencies and conflicts and select the most logically coherent local integration. This structure-preserving process maintains alignment with ongoing execution, mitigates ambiguity and inconsistency, and reuses shared subtasks to reduce redundant execution. We also introduce CHIRP (Continual Household Instruction Reconciliation and Planning), a text-based benchmark of 120 episodes across eight household environments and six categories of everyday activities. On CHIRP, CIRRA achieves 74.2% decision agreement, exceeding the strongest replanning baseline by 30 percentage points; every correct fusion decision yields a correctly placed, conflict-free schedule. On a Unitree G1 humanoid, CIRRA interrupts ongoing skills at the correct moment in every trial and significantly outperforms all baselines on every metric.

cs.RO↗
arXiv2026

Permanent Thermodynamic Mpemba Inversion from Quantum-Jump Feedback

We show that a common quantum-jump feedback protocol can permanently reverse the nonequilibrium free-energy ordering of two prescribed initial states while preserving their Gibbs equilibrium. The construction exploits collective compensation between monitored channels: their feedback corrections cancel at equilibrium but remain active during relaxation. This balance preserves free-energy monotonicity while allowing the relaxation modes to be reshaped. We prove that eliminating the complete slow-sector contribution of the initially higher-free-energy state, while retaining it for the comparison state, produces distinct asymptotic decay exponents. Their free-energy ratio then vanishes at long times, guaranteeing a permanent thermodynamic quantum Mpemba inversion under the same controlled dynamics. A thermal qutrit realizes the mechanism through coherence interference and exhibits distinct detection thresholds for spectral selection and exact slow-sector cancellation under feedback retuning.

quant-ph↗
arXiv2026

GRPODropout: Less is More for Online Reinforcement Learning Rollouts

Reinforcement learning (RL) methods such as GRPO substantially improve large language model reasoning but often suffer from policy entropy collapse: the loss of sampling diversity weakens exploration and limits further improvement. Existing methods address this issue either through algorithm-level interventions, such as reward modification and entropy/KL regularization, or through token-level reweighting. We investigate a complementary perspective: entropy collapse can also be mitigated by changing which generated rollouts contribute to policy updates. Under the same sampling budget, not all rollouts contribute positively to an update, and selectively excluding some can improve learning. To address this, we propose GRPODropout: before the standard update, we use a simple strategy that selectively removes a small number of high-probability positive-advantage rollouts and recenters the retained advantages. To motivate this design, we develop a rollout-level theoretical analysis that guides method design and threshold selection. The method changes only rollout usage, and adds negligible computational overhead. Experiments show higher accuracy than original GRPO and higher actor entropy while using fewer rollout samples for updates, illustrating "less is more." This work provides insight into RL rollout usage: removing some rollouts can improve performance. Code is available at https://github.com/hexuandeng/GRPODropout/.

cs.LG↗
arXiv2026

Can Agentic Trading Systems Pay for Their Own Intelligence?

Large language model (LLM) agents are increasingly used in trading systems, where model reasoning, tool use, and continual decisions incur costs that are expected to produce trading value. Existing evaluations typically report performance metrics, but rarely examine agentic viability: whether dynamic LLM-mediated decisions convert their induced costs into measurable incremental profit. To apply this criterion, we introduce TradeLens, a trace-grounded diagnostic toolkit for evaluating agentic trading systems from their trading records, runtime traces, and deployment configurations. It reconstructs trading trajectories, attributes profit and cost to interpretable evidence, and diagnoses whether and why an agent pays for its own intelligence. We conduct extensive analysis across backbone models, capital scales, trading frequencies, and system architectures, together with deployment discussion. Our results show that viability hinges on intelligence-to-profit conversion: models exhibit different failure patterns, such as poor asset selection in DeepSeek-V3.2 and negative timing in GLM-4.7, while capital scale, trading frequency, and architecture matter primarily in these runs, especially through their effects on decision-attributed timing value. These findings reframe the evaluation of LLMbased trading agents from capability-centric performance ranking to trace-grounded diagnosis of intelligence-to-profit conversion. Our code is available at https://github.com/ParadooxAI/TradeLens.

cs.AI↗
arXiv2026

Sequential Random Sampling PIR with Multiple Colluding Servers in DNA-Based Data Storage

As DNA-based data storage evolves, protecting user privacy during data retrieval has become increasingly important. We study sequential random sampling DNA private information retrieval (SRS DNA PIR) with multiple colluding random sampling servers, where the database is partitioned into servers of equal size. We investigate the tradeoff between the download cost, defined as the expected number of queries, and the privacy leakage, measured by mutual information. We derive lower bounds on this tradeoff, including a bound given by an optimization problem. This bound is tight when each server stores two files, and we construct schemes that attain it. For servers of any size, we construct schemes that apply a single-server scheme to a randomly selected subset of servers.

cs.IT↗
arXiv2026

HARMONY: Hierarchical Agentic Reasoning for MONocular Image-to-Scene Synthesis

Compositional 3D scene reconstruction has recently been explored from two directions: agentic reasoning that provides semantic understanding of spatial relationships but lacks precise alignment with input images; and visual geometry foundation models that predict dense point maps from input images but the reconstruction quality is limited. Therefore, recovering a complete 3D scene from a single monocular image with accurate inter-object relationships and high-fidelity reconstruction quality remains challenging. In this paper, we present HARMONY, a hierarchical chain-of-thought framework that leverages both agentic reasoning and visual geometry foundation. Given an image of an indoor scene, starting from an empty 3D floorplan, HARMONY first calibrates the camera against the reference image to establish a semantically-grounded spatial frame, then uses agentic VLM reasoning to recover the 3D room layout and an initial placement order. It then places the objects in a hierarchical order, from wall-mounted elements, free-standing furniture, to dependent decorations on top of furniture. We also use depth-first traversal for furniture so each placement conditions on previously resolved structure and a reflective feedback loop to avoid error accumulation. After each object placement by VLM, we use the point cloud estimations to perform geometry-based refinement so that the rendered image aligns better with the input. HARMONY can produce 3D scenes that are semantically consistent and perceptually aligned with the reference image, extending single-image compositional reconstruction to complex indoor scene images. Experiments on synthetic and real-world images demonstrate that HARMONY outperforms the evaluated reconstruction baselines, while qualitative comparisons with GPT-6 Astra suggest more faithful object arrangements and better preservation of scene details.

cs.CV↗
arXiv2026

Nuclear mass table in deformed relativistic Hartree-Bogoliubov theory in continuum, III: nuclei with $8 \leq Z \leq 120$

The mass table in the deformed relativistic Hartree-Bogoliubov theory in continuum (DRHBc) with the PC-PK1 density functional has been established for nuclei with $8 \leq Z \leq 120$, extended from the previous works for even-even nuclei [Zhang et al. (DRHBc mass table collaboration), At. Data Nucl. Data Tables 144, 101488 (2022)] and for even-$Z$ nuclei [Guo et al. (DRHBc mass table collaboration), At. Data Nucl. Data Tables 158, 101661 (2024)]. The calculated binding energies, two- and one-nucleon separation energies, root-mean-square (rms) radii of neutron, proton, matter, and charge distributions, quadrupole deformations, neutron and proton Fermi surfaces, and the blocked neutron (proton) orbitals of odd-$N$ ($Z$) nuclei are tabulated and compared with the available experimental data. A total of 9495 nuclei are predicted to be bound, with an rms deviation of 1.444 MeV from the 2380 mass data. Good agreement with the available experimental pairing gaps, $α$ decay energies, and charge radii is also achieved. The accuracies of the calculated nuclear masses and nucleon separation energies as well as the prediction for drip lines are compared with those obtained by other relativistic and nonrelativistic density functional calculations. It turns out that the DRHBc theory with PC-PK1 provides one of the best microscopic descriptions for nuclear masses. The systematics of nucleon separation energies, pairing gaps, pairing energies, two-nucleon gaps, $α$ decay energies, rms radii, quadrupole deformations, potential energy curves, neutron density distributions, and neutron mean-field potentials are discussed.

nucl-th↗
arXiv2026

Asymptotic Spectral Bounds under Odd-Girth Constraints

Odd girth and the sum of the largest and smallest adjacency eigenvalues are two common indicators of how close a graph is to being bipartite. This paper investigates the asymptotic behavior of this eigenvalue sum under odd-girth constraints. We study the associated abstract moment problem over finite real lists satisfying the vanishing odd-moment identities imposed by odd girth at least $g$ and the standard second-moment bound for graph spectra. We prove that the supremum of $(λ_1+λ_n)/n$ over these lists lies between $(1-o(1))(\log g)^2/g^3$ and $(10/7+o(1))(\log g)^2/g^3$ as $g\to\infty$ through the odd integers. The upper bound applies in particular to graphs of odd girth at least $g$. For regular graphs of odd girth $g\geq5$, we obtain a stronger bound $(λ_1+λ_n)/n \leq 12/((g-1)(g-2)(g-3))$, which is optimal up to a constant factor.

math.CO↗
arXiv2026

On the Role of Diffractive Production in Precision Studies of W and Z Bosons at the LHC

The increasing precision of measurements at the Large Hadron Collider requires a detailed understanding of all contributions to electroweak boson production. We estimate the impact of single-diffractive W and Z production on precision observables at $\sqrt{s}=5$, 7, 8, and 13 TeV. The non-diffractive baseline is calculated with DYTurbo, while Herwig provides the relative single-diffractive contribution and its transverse-momentum dependence. Factorization breaking is incorporated through a $p_T$-dependent rapidity-gap survival probability calculated with the dynamic multiparton-interaction model of Pythia8. The diffractive Asimov spectrum is constructed by deterministic bin-by-bin reweighting of the same high-numerical-precision DYTurbo cross section used for the non-diffractive baseline. With the non-perturbative parameters profiled, the nominal relative shifts in $α_s$ are -0.0072%, -0.043%, -0.070%, and -0.067% at 5, 7, 8, and 13 TeV, respectively. Five Pythia8 Pomeron-flux and diffractive-PDF configurations give a maximum spread of $9.4\times10^{-6}$ in $Δα_s$. In the W-mass study, the largest bias from an unmodelled survived single-diffractive contribution is 1.58 MeV, and the largest residual after applying the corresponding model-matched template correction is 1.14 MeV. These shifts are below the relevant fit precision, and no phenomenologically significant impact on $m_W$ is expected within the tested models.

hep-ph↗
arXiv2026

SimpleTouch: Can Vision-Language-Action Models Master Contact-Rich Manipulation Without Tactile Policy Pretraining?

Tactile sensing provides essential contact information for robotic manipulation, yet incorporating it into pretrained vision-language-action (VLA) models remains challenging. A common concern is that simply introducing touch during task-specific fine-tuning may fail to bridge the cross-modal gap, yielding limited gains or even reduced success. Consequently, existing methods often rely on large-scale tactile policy pretraining or separate visuotactile alignment, adding data requirements and training stages. We introduce SimpleTouch, a simple VLA extension that augments $π_{0.5}$ with a tactile expert, to test whether these additional stages are necessary. Leveraging all tokens from a frozen pretrained tactile encoder, the expert learns from action supervision and multi-horizon prediction of future tactile latents. This single-stage training uses only task demonstrations, without additional tactile policy pretraining or separate alignment. With 50 demonstrations per task, SimpleTouch achieves the highest success rate among evaluated methods on all six UniVTAC tasks. Its average success rate reaches 77.5%, compared with 45.2% for FTP-$π_{0.5}$ and 66.7% for FTP-1, corresponding to gains of 32.3 and 10.8 percentage points, respectively. Across four real-world tasks, it averages 71.3%, exceeding FTP-1 by 8.8 percentage points. These results demonstrate that, given pretrained VLA and tactile representations, additional tactile policy pretraining is not a prerequisite for strong performance on these tasks, offering a simpler route to contact-rich manipulation. Project page: https://simpletouch-robot.github.io/

cs.RO↗
arXiv2026

The Coverage Depth Problem in Distributed DNA Data Storage

Random sampling in DNA sequencing produces repeated reads, increasing retrieval latency and sequencing cost. We study the coverage-depth problem for full-message recovery in distributed DNA storage under noiseless uniform sampling, where strands are partitioned among $M$ containers and one strand is independently sampled with replacement from each container per round. For arbitrary linear codes and ordered partitions, we derive exact formulas for the recovery-time distribution and expectation. We prove that MDS codes, whenever they exist, are optimal for every fixed partition, and establish a universal lower bound on the expected total read cost together with its equality conditions. For MDS codes, we identify container-size regimes that yield genuine savings in total reads and regimes that provide only parallelism without changing the asymptotic sequencing cost. For simplex codes, we prove that the $q$-ary simplex code is, up to isomorphism, the unique single-container minimizer among codes with the same parameters, resolving a recent conjecture by Bertuzzo, Ravagnani, and Yaakobi. We further construct a partition attaining the minimum total read cost and derive bounds for intermediate and balanced partitions. These results clarify when distributed sampling reduces latency alone and when it also reduces sequencing cost.

cs.IT↗
arXiv2026

ePACT: Energy-Performance-Aware Commitment Tracking for LLM Serving

Reducing LLM serving energy does not by itself guarantee lower deployment cost when electricity procurement exposes operators to unfavorable deviations from preset commitments. We study hourly commitments with positive, potentially asymmetric costs for overuse and underuse, and formulate energy-Performance-Aware Commitment Tracking: minimize deviation costs subject to request-level service requirements. We implement ePACT, a two-level controller that adjusts serving capacity and GPU clocks as requests arrive. A global planner updates interval energy targets from measured consumption and the remaining hourly commitment. A local decision maker predicts candidate configurations' energy and completion times, checks predicted deadline misses, and selects among admitted configurations by asymmetric target-deviation cost, with a service-first fallback. Coarse-to-fine action search runs asynchronously with serving. We evaluate ePACT through single-hour comparisons, controller ablations, and full-day trace simulations for H20 and H200 GPU pools. In the 24-hour simulations, ePACT reduces the asymmetric deviation cost by $73.8\%$ and $75.7\%$ relative to vLLM while retaining near-vLLM SLO attainment. Mean absolute hourly deviations are $2.16\%$ and $2.31\%$, respectively.

cs.DC↗
arXiv2026

Distilled Reinforcement Learning for LLM Post-training

Large language model (LLM) post-training is essential for improving reasoning, adaptation, and alignment. Existing methods mainly follow two paradigms: reinforcement learning (RL) and on-policy distillation (OPD). However, RL relies on coarse-grained outcome supervision, resulting in difficult credit assignment and limited capability to acquire new knowledge. OPD, meanwhile, unconditionally matches teacher logits through KL divergence, which creates a dilemma: similar teachers provide little new knowledge, while substantially different teachers often yield ineffective guidance, largely restricting OPD to within-family distillation. We propose Distilled Reinforcement Learning (Distilled RL), which integrates teacher supervision into the RL objective to provide fine-grained guidance, selectively transfer new knowledge and avoid unconditional imitation. Distilled RL contains three components: reverse importance sampling with clipping, negative sample reset, and sequence-level geometric normalization. Through a concise and interpretable case study, we demonstrate that Distilled RL can effectively transfer previously unavailable knowledge from a teacher model to a student model. Extensive experiments across both within-family and cross-family distillation settings show that Distilled RL substantially outperforms standard RL and OPD in terms of both pass@1 and pass@k. Our code is available at https://github.com/597358816/Distilled-RL.

cs.LG↗
arXiv2026

Explicit Constructions of Maximum-Cardinality Families of Plateaued Functions with Pairwise Disjoint Walsh Supports

Families of plateaued Boolean functions with pairwise disjoint Walsh supports are useful in secondary constructions of cryptographic Boolean functions. Of particular interest are maximum-cardinality families whose members admit no nonzero linear structures. To the best of our knowledge, the previously known general construction attaining both properties is spectral (Hodžić et al., IEEE Trans. Inf. Theory 65(9): 5865--5879, 2019). In that work, explicit algebraic normal forms are not generally provided, and no general method is established for prescribing a common algebraic degree for all family members. In this paper, we present two new explicit algebraic constructions within a unified framework, one based on linear functions and the other on partially linear functions with bent components. Let $p\geq 2$ and $q\geq 0$ satisfy $q<2^p-p-1$, and set $m=p+q$. Both constructions yield maximum-cardinality families of $2^{q+1}$ $(q+1)$-plateaued Boolean functions with pairwise disjoint Walsh supports. No member admits a nonzero linear structure, and every member has an explicit generalized Maiorana--McFarland representation. The first construction produces functions in $m+p+1$ variables and realizes any prescribed common algebraic degree $3\leq d\leq p+1$, provided that $q<\sum_{i=2}^{d-1}\binom{p}{i}$; its maximum attainable degree $p+1$ is optimal. The second construction produces functions in $n+p+1$ variables, where $n>m$ and $n-m$ is even, and realizes any prescribed common algebraic degree $3\leq d\leq p+(n-m)/2$, provided that $q<\sum_{i=2}^{\min\{d-1,p\}}\binom{p}{i}$; its maximum attainable degree $p+(n-m)/2$ is next-to-optimal.

cs.IT↗