arXiv subjects

Xi Chen

Publications and source records attributed to Xi Chen.

At least 37 records · Page 2Linked to original sources

arXiv2026

MLLMs Know When Before Speaking: Revealing and Recovering Temporal Grounding via Attention Cues

Video temporal grounding (VTG), which localizes the start and end times of a queried event in an untrimmed video, is a key test of whether multimodal large language models (MLLMs) understand not only what happens but also when it happens. Although modern MLLMs describe video content fluently, their timestamp predictions remain unreliable, while existing remedies either require costly post-training on temporal annotations or rely on coarse training-free heuristics. In this work, we probe the cross-modal attention of MLLMs and uncover a perception-generation gap. Our key finding is that MLLMs often know the target interval during prefill, but lose this signal when generating the final answer. In the prefill stage, a sparse set of attention heads, which we call Temporal Grounding Heads (TG-Heads), concentrates query-to-video attention on the ground-truth interval. During autoregressive decoding, however, the answer tokens shift attention away from this interval toward visually salient but query-irrelevant segments. This observation motivates an inference-time read-then-regenerate framework. We first convert TG-Head prefill attention into a debiased frame-level relevance signal and extract the high-attention interval it highlights. We then re-invoke the MLLM with visual context restricted to this interval using video cropping. Without parameter updates or architectural changes, our framework consistently improves MiMo-VL, Qwen3-VL, and Molmo2 on three benchmarks, with gains of up to +3.5 mIoU. The project website can be found at https://ddz16.github.io/mllmsknowwhen.github.io/.

cs.CV↗

arXiv2026

Learning Spatiotemporal Sensitivity in Video LLMs via Counterfactual Reinforcement Learning

Video large language models (Video LLMs) can achieve strong video-QA accuracy without reliably tracking spatiotemporal dynamics. A model may answer a motion question from static cues, for example, and give the same prediction even after the underlying motion is reversed. Correctness-based reinforcement learning does not directly address this problem because it rewards the final answer without requiring the policy to respond to task-relevant video dynamics. We propose Counterfactual Relational Policy Optimization (CRPO), which explicitly trains Video LLMs to respond to controlled changes in the visual input. For each training example, CRPO constructs a counterfactual video, such as a horizontally flipped or temporally reversed version of the original, and jointly optimizes rollouts from both videos under a shared policy. Factual supervision anchors what the model should answer, while counterfactual supervision constrains when that answer should change: predictions should change when an intervention alters task-relevant dynamics and remain stable when the queried property is preserved. This coupling provides a direct behavioral learning signal without requiring ground-truth labels for transformed videos or annotated spatiotemporal reasoning traces, while discouraging indiscriminate answer changes. To evaluate this property, we introduce DyBench, a paired counterfactual benchmark with 3{,}014 videos and a strict pair-accuracy metric. Across paired spatiotemporal evaluations and standard video benchmarks, CRPO improves sensitivity to motion and temporal changes while improving performance on general video understanding. The gains also extend to segment reordering, a transformation never used during training, suggesting that CRPO learns sensitivity to video dynamics beyond the training interventions. The project website can be found at https://ddz16.github.io/crpo.github.io/ .

cs.CV↗

arXiv2026

Can a Robot Read Braille? - Learning to Adapt Contact via Imitation Learning for Tactile Braille Recognition

For people who are blind, touch provides an essen-tial channel for accessing written information through Braille. Bringing a similar capability to robots requires them not only to recognize tactile patterns, but also to actively establish physical contact that makes those patterns readable. Yet existing robotic Braille readers largely focus on recognition after contact, leaving contact establishment itself insufficiently addressed. We present an adaptive-contact framework for robotic tactile Braille reading that assesses contact quality and physically corrects unsuitable contact before recognition and reconstruc-tion. Multi-Head Policy Learning uses expert-guided contact-adjustment demonstrations to jointly learn contact acceptability and pose corrections. During deployment, the robot iteratively evaluates and re-establishes contact, retaining reliable tactile observations for pose-aware fusion and Braille reconstruction. Across 20 physical Braille plates used for learning and eval-uation, the proposed approach achieves 94.0% tactile quality and 88.6% tactile reconstruction on the ten online-evaluation plates. These results demonstrate the importance of actively establishing readable contact, rather than relying solely on recognition under imperfect tactile observations, for reliable robotic Braille reading.

cs.RO↗

arXiv2026

VLALight: Lightweight Vision-Language-Action Models for Emergency-Aware Traffic Signal Control

Traffic signal control (TSC) is essential for mitigating urban congestion. Recent advances in vision-language models (VLMs) enable richer interpretation of intersection scenes, opening new opportunities for visual-context-aware TSC. However, the loose coupling and repeated information conversion between modules can lead to the loss of fine-grained visual details, while sequential inference introduces substantial latency. To address these limitations, we propose VLALight, a lightweight end-to-end vision-language-action framework that directly maps intersection observations and signal-phase information to discrete signal actions. To handle the multi-view nature of TSC, VLALight combines multiple directional camera views into a unified visual input and uses textual instructions to establish their correspondence with traffic movements and signal phases. This design enables direct action prediction with a compact 0.5 B-parameter model, without intermediate image-to-text descriptions or handcrafted traffic-state representations. Experiments show that VLALight delivers the best emergency-vehicle service of all compared methods, reducing pooled emergency waiting time by 21.1% over the cascaded VLMLight while running in real time on local hardware and generalizing to unseen intersection topologies and traffic-flow patterns.

cs.CV↗

arXiv2026

Attention Sinks and Outliers in Attention Residuals

We propose OASIS, an outlier- and sink-aware method that stabilizes dual-normalized attention-residual architectures through explicit null routing and token-to-depth null coupling. AttnResidual introduces an additional depth-wise normalization channel that improves inter-layer routing flexibility but can also amplify attention sinks, activation outliers, and low-bit quantization error. OASIS builds on explicit Softmax1-based null routes at both the token and depth levels and uses token-level null evidence to downweight depth branches exhibiting stronger null behavior. Theoretically, we characterize a conditional mechanism for sink-like attention concentration under dual normalization, offering insight into the low-bit sensitivity observed in AttnResidual. Experimentally, we compare OASIS against five baselines on three language-model backbones and multiple language-modeling, reasoning, and long-context benchmarks and observe consistent improvements in both attention sink mitigation and post-quantization performance. Notably, relative to Vanilla AttnResidual, OASIS reduces maximum infinity norm by 81.75% and average kurtosis by 95.90%, lowers W8A8 perplexity by 82.00%, and improves W4A4 GSM8K Pass@1 by 42.11% on average across LLaMA-3.2-1B, Qwen3-0.6B, and Phi-4. Code is available at: https://github.com/robinzixuan/OASIS.

cs.LG↗

arXiv2026

Antichain polynomials of products of chains and minuscule posets

This paper studies the antichain polynomials of $[k]\times P$, where $P$ is a connected minuscule poset. We give a formula for the number of antichains, counted by size, of an arbitrary poset. Using this formula, we present necessary and sufficient conditions for the palindromicity of antichain polynomials for two infinite families of connected minuscule posets. We show that, for every connected minuscule poset $P$, if the antichain polynomial of $[k]\times P$ is palindromic, then it has only real and strictly negative zeros. This result, in particular, gives an affirmative answer to Ding-Dong's conjecture about $γ$-positivity of the antichain polynomial of $[k]\times P$. By constructing a bijection between antichains and labeled Dyck paths, we also give a layer-refined enumeration of the antichains in $[2]\times[m]\times[n]$. We establish a relation between such antichains and Clar covers of the hexagonal flakes $O(2,m,n)$, thus prove a conjectured determinantal formula for a family of Zhang-Zhang polynomials. Real-rootedness and stability results are also obtained when the shortest chain has length at most two. Finally, we present infinitely many connected Peck posets whose antichain polynomials are not unimodal, disproving the log-concavity conjecture of Ding and Dong.

math.CO↗

arXiv2026

Antisymmetric breathing in altermagnetic skyrmions

A skyrmion in an altermagnet with $d$ wave symmetry consists of two elliptical sublattice textures with perpendicular long axes. For each sublattice component $η=A,B$, we define an effective skyrmion radius $R_η=\sqrt{a_ηb_η}$, where $a_η$ and $b_η$ are the distances from the skyrmion center to its boundary along $y$ and $x$, respectively. For the anisotropic exchange parameters studied, the equilibrium radius at zero field is smaller than in a reference with parallel sublattice textures and otherwise identical parameters. A magnetic field perpendicular to the film expands one sublattice skyrmion and contracts the other, generating a radius difference $\dR=R_A-R_B$ and a net magnetic moment. The exchange modulation used to represent uniaxial strain also produces a nonzero radius difference at zero field. Because the strong and weak exchange directions are interchanged between the two sublattices, a common directional change of the exchange couplings increases one radius and decreases the other. Unlike the magnetic coupling, this mechanism vanishes when the two sublattice exchange tensors become identical. The radius difference also supports an antisymmetric breathing mode. After a short field pulse, it oscillates in quadrature with the uniform helicity, the common rotation of the wall magnetization within the film plane, at $49.5\,\mathrm{GHz}$ for the reference parameters.

cond-mat.mes-hall↗

arXiv2026

Combinatorial aspects of the Delannoy Lattice

The Delannoy numbers $d(n,k)$ count lattice paths from $(0,0)$ to $(n-k,k)$ using steps $(1,0),(0,1)$ and $(1,1)$. This paper introduces a graded poset $\mathcal{D}_n$ on the Delannoy paths ending on the line $x+y=n$, whose rank-generating function is the Delannoy polynomial $d_n(x)=\sum_{k=0}^n d(n,k)x^k$. We prove that $\\mathcal{D}_n$ is a self-dual lattice, which is call the Delannoy lattice. By establishing an explicit symmetric Boolean decomposition, we show that $\mathcal{D}_n$ is a symmetric Boolean order, thereby recovering the $γ$-positivity of $d_n(x)$. Such a decomposition is refined to a symmetric chain decomposition with the chain cover property, and is applied to determine all maximum antichains. We also investigate other combinatorial aspects of $\mathcal{D}_n$, including supersolvability, the Möbius number, characteristic polynomials, and zeta polynomials.

math.CO↗

arXiv2026

Logarithmic concentration for the focusing cubic Schrödinger equation on the two-dimensional torus

We construct a smooth solution of the focusing cubic nonlinear Schrödinger equation on a square two-dimensional torus which is global in both time directions and concentrates at one point as time tends to positive infinity. Its mass is the mass of the Euclidean ground state and its energy is zero. If $λ(t)$ denotes its concentration scale and $L$ the period, then $L/λ(t)=2\log t+\frac{11}{2}\log\log t+O(1)$. The solution approaches a phased, periodized ground state with an error tending to zero in every fixed Sobolev space. In particular, its $H^s$ norm is asymptotic to an explicit constant times $(\log t)^s$ for every $s>0$. We also prove uniqueness, up to constant phase and time translation, within the quantitative single-profile asymptotic class used in the construction. The mechanism is the exponentially small interaction of the profile with its periodic images. Exact mass and energy constraints select the concentrating branch, while a positive energy on the moving constrained space controls the terminal-value problem at every fixed regularity order.

math.AP↗

arXiv2026

Co-Fabric: Breaking Host-Domain Boundaries for Unified xPU Interconnection

Large-model parameters have grown beyond the capacity of a single xPU, dispersing across multiple xPUs spanning distinct host domains, where xPU-to-xPU communication dominates overall system efficiency. Existing scale-up interconnect remains inadequate: network-based solutions built on Ethernet--such as RoCE (RDMA over Converged Ethernet)--introduce specific message-semantics and protocol-stack characteristics, and rely on fragmented per-host addressing, while conventional host-based fabrics are confined to a single host domain and lack cross-host unified addressing. This paper presents Co-Fabric, a bus-based interconnect that, unlike conventional bus designs, breaks host-domain boundaries to deliver unified xPU interconnection for scale-up superpods. Co-Fabric makes three contributions: a streamlined four-layer protocol stack achieving nanosecond-scale processing latency with native reliability; a cross-domain scaling and P2P mechanism that routes using port identifiers embedded in the packet header; and a unified address space built on shadow-device auto-enumeration. On a 64-xPU 3D-Mesh system, Co-Fabric cuts inter-node communication latency by over 50% and improves bandwidth by 2-5x over RoCE, accelerating DeepSeek R1 inference by 30%-80%. Moreover, since its streamlined four-layer protocol stack and higher data-communication efficiency reduce protocol and processing overhead relative to the Ethernet-based RoCE stack, Co-Fabric cuts the cost and power of the interconnect itself by up to 80% and 5%, respectively. These results demonstrate Co-Fabric's advantage for AI computing centers.

cs.DC↗

arXiv2026

Spin-Orbit-Mediated Magnetization Transfer in the Fermi-Hubbard Model

We demonstrate spin--orbit-coupling (SOC) catalysis of magnetization-sector transfer in the half-filled Fermi--Hubbard model. Without SOC, conservation of total magnetization confines the dynamics to the initial sector, preventing an antiferromagnetically correlated state from reaching the polarized ferromagnetic sector under a Zeeman ramp. A transient SOC control lifts this obstruction by coupling otherwise disconnected magnetization sectors and converting symmetry-protected crossings into avoided crossings, thereby opening a finite-gap pathway for magnetic-state conversion. We further accelerate the SOC-enabled dynamics beyond the adiabatic timescale using gradient-ascent pulse engineering (GRAPE) and a variational quantum circuit. Both approaches achieve rapid magnetization transfer in one- and two-dimensional Fermi--Hubbard lattices. Our results establish transient SOC as a controllable catalyst for overcoming symmetry-imposed dynamical constraints, while optimal control sets the timescale for the resulting magnetization-sector transfer.

quant-ph↗

arXiv2026

Programmable Coherent Memory Kernels for Quantum Reservoir Computing in Waveguide QED

Reservoir computing requires not only long memory, but also memory distributed over the timescales relevant to a given task. In most quantum reservoir computing architectures, however, the memory profile emerges from intrinsic dynamics and cannot be directly engineered. Here we introduce a waveguide-QED quantum reservoir in which coherent memory return is controlled by the coupling geometry. The reservoir consists of a driven Kerr-nonlinear resonator coupled to a one-dimensional waveguide at spatially separated points. An unmeasured propagating field carries information about past inputs and coherently returns it to the resonator after a finite propagation time, forming a non-Markovian feedback channel without intermediate measurement or classical reinjection. Delay-resolved memory benchmarks reveal two complementary functions: waveguide propagation determines when past information returns, whereas Kerr dynamics convert the returned field into nonlinear temporal features accessible through a linear readout. NARMA-$n$ prediction shows that the optimal feedback delay shifts systematically with task order and approximately tracks the explicit input-product lag. These results establish coherent delayed feedback as a mechanism for engineering task-relevant memory in quantum reservoir computing.

quant-ph↗

arXiv2026

Combinatorial Inference on the Optimal Assortment in Multinomial Logit Models

Assortment optimization has received active explorations in the past few decades due to its practical importance. Despite the extensive literature dealing with optimization algorithms and latent score estimation, uncertainty quantification for the optimal assortment still needs to be explored and is of great practical significance. Instead of estimating and recovering the complete optimal offer set, decision-makers may only be interested in testing whether a given property holds true for the optimal assortment, such as whether they should include several products of interest in the optimal set, or how many categories of products the optimal set should include. This paper proposes a novel inferential framework for testing such properties. We consider the widely adopted multinomial logit (MNL) model, where we assume that each customer will purchase an item within the offered products with a probability proportional to the underlying preference score associated with the product. We reduce inferring a general optimal assortment property to quantifying the uncertainty associated with the sign change point detection of the marginal revenue gaps. We show the asymptotic normality of the marginal revenue gap estimator, and construct a maximum statistic via the gap estimators to detect the sign change point. By approximating the distribution of the maximum statistic with multiplier bootstrap techniques, we propose a valid testing procedure. We also conduct numerical experiments to assess the performance of our method.

stat.ML↗

arXiv2026

Tuning-Free Covariance-Aware Sequential Shrinkage for Multi-Source Estimation

Modern statistical learning problems often involve multiple related data sets, in which learning efficiency on a target set can be improved by borrowing information from related sources, while source heterogeneity may introduce bias. Existing approaches are limited by suboptimal performance in multi-source settings, insufficient use of covariance information, or the computational burden of tuning procedures. We propose a covariance-aware shrinkage framework that constructs shrinkage directions using covariance information to improve efficiency. We establish finite-sample risk bounds that yield an explicit risk-improving interval for the shrinkage size, making the transfer strength fully data-driven. When multiple source sets are available, we further propose a sequential algorithm that applies source-specific shrinkage updates according to a priority score. Under a mixed-source separation condition, the estimator asymptotically attains the oracle risk and, when the pooled discrepancy is large, strictly improves over single-step shrinkage. The framework is further extended to a broad class of smooth M-estimation problems. Numerical studies show substantial gains over competing methods, especially when the source data sets are highly heterogeneous.

stat.ME↗

arXiv2026

Talbot effect for the periodic Benjamin--Ono equation

We study the dependence on time of the spatial regularity of solutions to the periodic Benjamin--Ono equation with real, mean-zero initial data of bounded variation. For every datum with a nonzero jump, we prove that continuity and essential boundedness at an irrational time $t=2πα$ are equivalent to the arithmetic condition $\sum_j\log(q_{j+1})/\sqrt{q_j}<\infty$, where $q_j$ are the continued-fraction denominators of $α$. We also determine the exact Hölder regularity and the Besov scale for spatial exponents $2<p\leq\infty$. We derive a high-frequency energy formula and prove the same sharp local criteria on every spatial interval at every irrational time for an open dense set of BV data. At rational times, piecewise smooth data give finite sums of logarithmic and jump kernels modulo a continuous remainder. For arbitrary BV data with a jump, the nonlinear and linear solutions have different logarithmic Poisson coefficients at every sufficiently large reduced denominator, uniformly in the numerator. The proofs combine the smoothing of Tao's gauge transform with estimates for quadratic Fourier series. A finite averaging argument isolates an atom of the initial gauge measure while retaining the real nonlinear reconstruction.

math.AP↗

arXiv2026

Infinite cascades for the defocusing cubic half-wave equation on the torus

We construct global solutions of the periodic defocusing cubic half-wave equation whose $H^s$ norms grow exponentially as $t\to+\infty$ for every $1/2<s<3/2$. Such solutions exist at every positive mass. The construction starts from explicit concentrating trajectories of a linearly perturbed Szego equation and solves an infinite-time final-value problem for the full half-wave flow, including its negative-frequency component. We obtain the exact growth rate and conserved quantities. Finite Blaschke products allow us to prescribe finitely many concentration points and their relative widths, and we compute the limiting critical kinetic-energy measures. We also identify the endpoint Fourier decay of the constructed data and prove the sharp logarithmic regularity threshold on the resonant mass slice and for generic scalar parameters. In particular, to the best of our knowledge, this provides the first example of a genuine infinite cascade for a defocusing fractional nonlinear Schrödinger equation on the torus.

math.AP↗

arXiv2026

AdaReP:Adaptive Re-Planning under Model Mismatch for Neural World-Model Predictive Control

Neural world models coupled with model predictive control (MPC) replan at every environment step to bound accumulated prediction error, but this incurs substantial computational overhead. Reusing a cached plan reduces this overhead, yet its effectiveness depends on how prediction mismatch propagates through the local dynamics. We analyze this trade-off with a perturbation-based dynamic-regret framework and show that stale-plan penalties scale with the reuse tolerance, the accumulated mismatch since the last replanning step, and the local dynamics sensitivity. Based on this structure, we propose AdaReP, a training-free wrapper that adapts the replanning tolerance online using the current deviation from the cached rollout and a local sensitivity estimate, without modifying the learned world model or planner. Across image-space planning, latent-space control, and real-world robotic manipulation, AdaReP substantially reduces planner-side computation while maintaining comparable task performance, including over 80% fewer queries on a 50-trial physical robot study.

cs.RO↗

arXiv2026

ArenaFlow: From Trajectory Ranking to Hierarchical Credit Propagation for Open-Ended Agent RL

Reinforcement learning has substantially improved large language model (LLM) agents in verifiable domains, but remains difficult to apply to open-ended agent tasks, where solutions are diverse and reliable scalar rewards are hard to obtain. Recent pairwise evaluation methods alleviate reward discrimination collapse by replacing pointwise scoring with relative preferences. However, they still compress rich comparative feedback into a single trajectory-level reward, obscuring decisive intermediate steps and preventing successful behaviors from being consolidated into reusable skills. We propose ArenaFlow, a hierarchical credit propagation framework for open-ended agent reinforcement learning. ArenaFlow leverages tournament-based relative ranking to derive trajectory-level reward signals. Each comparison is further equipped with structured reflective evaluation, which reveals three types of supervision: pivotal success steps, reusable strategy skills, and usage attribution of retrieved skills. At the step level, ArenaFlow propagates trajectory-level advantages to high-confidence pivotal steps according to tournament survival depth, enabling more targeted optimization of local reasoning behaviors. At the skill level, ArenaFlow estimates skill utility from group-level usage attribution and maintains a global skill memory through utility-aware updating, pruning, and retrieval. The resulting high-utility skills further serve as policy priors for future exploration. Extensive experiments validate ArenaFlow's effectiveness on open-ended agent tasks.

cs.CL↗