Peer Revenue Now accepting positions

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science

Sunday 27 September

Computer Vision

RepFlow: Reciprocal Supervision Improves Generation and Representation in Flow Models

Weili Zeng, Feng Tian, Shengqi Liu et al. (+1 more)

Generative models learn visual structure through denoising, yet their internal states are entangled with both noise level and network depth, making it difficult to obtain a stable visual representation from the generator itself. We introduce RepFlow, which learns such a representation from the generator's evolving computation and uses it to guide generation. Specifically, a separate timestep-free encoder is trained, through a timestep-conditioned predictor, to recover generator states across depths and noise levels from masked clean images. By excluding the reference noise and masked-out content from the encoder's input, we encourage the encoder to distill visual information that is recoverable from the visible image context and predictive of generator states. The representation learned from the generator's evolving states is then fed back to guide and improve the generator, whose updated states provide supervision for further representation learning, forming a reciprocal learning process. This reciprocal process improves multi-step generation and representation quality, as measured by frozen linear probing on ImageNet with latent-space SiT and pixel-space JiT, without an externally pretrained representation teacher. Across the two unconditional settings, FID decreases by $19.2$–$40.8\%$ relative to native training, while linear-probe accuracy improves by 6.80–10.04 percentage points over the best searched raw generator features. The learned representation also serves as a distributional metric for one-step JiT post-training, extending its role from instance-level alignment to distribution-level supervision.
Read the full abstract

All authors Weili Zeng, Feng Tian, Shengqi Liu, Yichao Yan

Numerical Analysis

Hierarchical low-rank compression exploiting symmetric boundary integral equations in transmission scattering

Yasuhiro Matsumoto, Taizo Maruyama, Qianxiang Ma et al. (+1 more)

We propose an approach using matrix symmetry to accelerate hierarchical low-rank compression for wave transmission scattering. For Helmholtz transmission problems, we introduce a symmetric Müller-like boundary integral equation formulation. Although not of the second kind, this formulation creates no difficulties for direct solvers. A one-point corrected quadrature in a Nyström discretization preserves the complex symmetry of the discretized system. This formulation is integrated into a variant of a hierarchical semiseparable direct solver. Within this framework, the computational workload of the low-rank approximation in the proxy method is halved by exploiting the symmetric relationship between the left and right coefficients. Furthermore, we extend this symmetry-exploiting approach to elastic transmission problems by using a symmetric Galerkin boundary element method. Numerical experiments on a multi-node computing cluster demonstrate that the symmetric Müller-like formulation for Helmholtz scattering achieves on average a 1.41-fold speedup compared to the non-symmetric baseline while maintaining third-order convergence. Furthermore, the symmetry-aware solver for elastic scattering is more than 1.5 times faster.
Read the full abstract

All authors Yasuhiro Matsumoto, Taizo Maruyama, Qianxiang Ma, Rio Yokota

Game Theory · Cross-listed from econ.TH

Learning from a Mixture of Information Sources

Nicole Immorlica, Brendan Lucier, Yaroslav Mukhin et al. (+2 more)

We often learn from multiple sources that convey information in different ways. How informative is it to know the source of a signal, and how is this informativeness shaped by the distribution of sources? We extend the standard (binary-state, binary-signal) Blackwell experiment model by introducing a commonly known distribution over signaling schemes, representing the distribution of information sources. We compare learning under two information models: source-aware, where decision makers observe a signaling scheme and its realization (e.g., raw reviews, search results), and source-blind, where only the signal realization is observed (e.g., aggregate ratings, LLM-generated summaries). We show that a mean-preserving spread in the distribution of signaling schemes translates into Blackwell dominance for source-aware decision makers, implying they are "risk-loving" in information sources. In contrast, it has no impact on source-blind decision makers. When learning from repeated draws of signaling schemes, source-blind decision makers learn more slowly. However, as long as the average signaling scheme is $\varepsilon$ away from being completely uninformative, source-blind learning can match source-aware learning by using at most $O(1/\varepsilon)$ times more data.
Read the full abstract

All authors Nicole Immorlica, Brendan Lucier, Yaroslav Mukhin, Clayton Thomas, Ruqing Xu

Numerical Analysis

Finance-Informed Operator Learning for Option Pricing with Quantum-Compatible Realizations

Jiarui Feng, Bingyang Hu, Yu Jiang et al. (+2 more)

Pricing European options under local volatility requires repeatedly solving a PDE whose coefficients change with recalibration, while practitioners need both prices and sensitivities across spot-time surfaces. Neural surrogates can amortize these solves, but near expiry the solution loses regularity, making curvature difficult to learn and allowing violations of no-arbitrage bounds. We propose a finance-informed Deep Operator Network (FI-DeepONet) that decomposes the pricing operator into an input-dependent Black-Scholes carrier and a learned correction. The carrier uses strike-line integrated variance, capturing the leading near-expiry curvature singularity, while a smooth monotone Financial Admissibility Layer enforces pointwise price bounds. We derive a short-maturity estimate and differentiated asymptotics for the exact correction, together with identities linking correction error to price, sensitivity, and PDE-residual errors. On in-distribution tests, FI-DeepONet reduces global relative price error by nearly an order of magnitude versus vanilla and physics-informed DeepONet baselines. On parameter-shift OOD tests within the same local-volatility family, generalization is moderate. On index-option data, the frozen model remains accurate without market-specific retraining, though it does not outperform the same-input analytic formula. We also give a quantum-compatible realization in which selected linear maps are exactly compiled or approximated by a restricted diagonal-orthogonal family before supervised adaptation.
Read the full abstract

All authors Jiarui Feng, Bingyang Hu, Yu Jiang, Changhong Mou, Yeyu Zhang

Computation and Language

CoLMbo-SV: A Grounded Language Model for Explainable Speaker Verification

Massa Baali, Sarthak Bisht, Ziyue Qiu et al. (+3 more)

Speaker verification systems achieve high accuracy but provide little account of the acoustic evidence behind their judgments. Making these systems inspectable requires exposing interpretable evidence while retaining the richer information on which their decisions depend. We present CoLMbo-SV, a speaker language model that combines strong speaker discrimination with structured, acoustically grounded comparison reports. By connecting a pretrained speaker encoder to a language model and supplying explicit acoustic measurements, CoLMbo-SV makes voice comparisons inspectable without restricting verification to the evidence verbalized in its reports. We additionally introduce VoxReason, paired recordings with measured acoustic properties and comparison reports filtered through numerical and qualitative checks, providing supervision for this combined capability. We also develop an evaluation framework that separates what acoustic information a speaker representation encodes, what influences the verification score, and what the generated report discusses. On VoxCeleb1-O, CoLMbo-SV achieves 0.99% EER, reducing verification error by approximately 80% relative to the strongest audio-language baseline fine-tuned on VoxReason, while attaining a numerical-grounding score of 0.82. Our analysis further demonstrates that acoustic correctness and decision relevance are distinct properties of an explanation, exposing a gap that numerical-grounding metrics miss. Together, these contributions substantially advance audio-language speaker verification, bring its accuracy toward that of dedicated speaker encoders while adding checkable acoustic reporting, and establish an empirical framework for connecting natural-language explanations to the decisions they explain.
Read the full abstract

All authors Massa Baali, Sarthak Bisht, Ziyue Qiu, Joseph Konan, Rita Singh, Bhiksha Raj

Computer Vision

Background Gradients Shape Memorization in Flow Matching

Xuanhua Yin, Boyu Wei, Shuyi Zhang et al. (+3 more)

Repetition is closely associated with memorization in generative models, but how other training images affect the retention and copying of targets remains unclear. We study this question in class-conditioned flow matching, where images outside the target set form the background. At fixed target repetition and same-class background row count, replacing repeated same-class images with distinct images reduces the target extraction rate from 80.7% to 18.0%. To explain this effect, we develop a paired-trajectory framework that isolates target-induced parameter displacement and the background gradient response to it. This response has an exact path-integrated curvature representation, connecting background loss geometry to target learning. Reciprocal response transfer between repeated and distinct backgrounds changes target retention and copying in both directions, establishing the response's causal role. After target removal, the response correction parallel to the target-induced displacement preserves approximately 90% of the copying effects of full response transfer. Directly scaling the displacement also changes copying without further training. The post-removal copying effects of reciprocal transfer are reproduced across datasets and architectures. Together, these results identify the background gradient response as a mechanism through which same-class training data shape the retention of target learning and the reproduction of target images.
Read the full abstract

All authors Xuanhua Yin, Boyu Wei, Shuyi Zhang, Shunqi Mao, Chuanzhi Xu, Weidong Cai

Computation and Language

Beyond Calibration: Do a Typed-Decision Model's Probabilities Obey the Probability Axioms?

Keyi Li, Yihao He and Quanyi Li

Typed-decision models such as TypeSafe's Jev answer a declared yes/no or multiple-choice question about a state with a probability instead of text, and their evaluations report accuracy and calibration. Neither requires that the probabilities a model gives to logically related questions fit together item by item, which is what a system that acts on those probabilities needs. We test this property, coherence, with a battery of logically linked questions that needs no labels. For 160 items from ChaosNLI and PubMedQA, each with three mutually exclusive labels, we ask whether the label is X, whether it is not X, whether it is one of the other two labels, and which label applies. On 480 negation pairs, Jev's probabilities for "the label is X" and "the label is not X" miss summing to one by 0.064 on average (95% CI 0.055 to 0.072). Qwen3.8-27B, run from its official BF16 weights, misses by 0.293 with first-token probabilities and by 0.122 with verbalized probabilities. The gap to the first-token readout persists on pairs where both systems give similar probabilities, without double-negation labels, and after averaging Jev's repeated calls. Jev is not coherent either: its violations are about five times its repeat noise, and it over-endorses statements about single labels, so that its three single-label probabilities sum to 1.14 on average. The two systems also fail differently. Qwen3.8-27B's first-token readout under-endorses the complement of a label whether or not the question contains "not", rejecting both a statement and its negation in 196 of 480 pairs, and it does not become more coherent where it is more confident, whereas Jev's violations concentrate where its answer is uncertain. Because the checks need no labels, they expose biases that appear only when question forms are compared, and inconsistencies within items.
Read the full abstract

Artificial Intelligence

WorldAgent: Verification-Guided Agentic Physical World Construction

Caoliwen Wang, Mengdi Wang, Yige Chen et al. (+13 more)

Constructing complex physical worlds from language requires coordinating extensive 3D environments, detailed structures and objects at different spatial scales, and interacting physical processes under both stated goals and implicit physical constraints. We present WorldAgent, an agentic framework for verification-guided physical world construction from a single natural-language prompt, without iterative user debugging. A world construction layer expands the prompt into a structured world specification and uses physical knowledge to build scenes and run numerical simulations. After every step, a verification layer inspects scene geometry and simulation states alongside rendered views. Failed checks guide automatic revisions to the specification and re-execution of the affected steps. Accepted worlds pass the required checks and remain editable for further inspection and resimulation. We introduce AgenticSimBench, on which WorldAgent achieves the best scores among the evaluated agent-based methods on five of seven metrics. In a 26-participant user study, it receives the highest mean ratings across all four criteria.
Read the full abstract

All authors Caoliwen Wang, Mengdi Wang, Yige Chen, Zejia Wu, Bowen Huang, Siyuan Chen, Guanxiong Chen, Lifu Wei, Heng Zhang, Qinghai Zhang, Yin Yang, Guandao Yang, Shiying Xiong, Peng Wang, Chenfanfu Jiang, Peter Yichen Chen

Hardware Architecture

MorphAtt: A Neuromorphic Accelerator for Efficient Multi-Head Attention Processing in Spiking Vision Transformers

Rachmad Vidya Wicaksana Putra, Amirhesam Jafari Rad and Muhammad Shafique

Spiking Vision Transformers (SViTs) are developed as an energy-efficient alternative to conventional ViTs for computer vision tasks at the edge. However, huge parameter counts and complex multi-head self-attention (MHSA) operations make it challenging to achieve high energy efficiency in SViT inference, especially in tightly constrained applications. To maximize efficiency gains of SViT processing, we propose MorphAtt, a novel digital accelerator that expedites SViT inference through streamlined processing. Specifically, it processes MHSA operations using cascaded hardware modules: a Spiking Query-Key-Value generator (SpikeQKV), a low-complexity Spiking Multi-Head Self-Attention engine (SpikeAtten), and Reparameterization Convolution (RepConv) modules. To mitigate traffic congestion in on-chip memory accesses and data reuse, specialized inter-module buffers are integrated within the dataflow. Under synthesis using 32nm CMOS technology, MorphAtt achieves 792-1605 GOPS of throughput, while incurring ~39-55 mW of power consumption and 1.5 mm^2 of area, which lead to 20.3-29.1 TOPS/W of energy efficiency. These results also demonstrate that our MorphAtt offers better performance and efficiency trade-offs than state-of-the-art, thereby enabling highly energy-efficient vision-based AI systems at the edge.
Read the full abstract

Systems and Control · Cross-listed from math.OC

An Adaptive, Parallel, and Inexact Newton Method for Large-scale Nonlinear Optimal Control

Luke Bhan, Michael W. Mahoney and Sen Na

We design adaptive overlapping temporal decomposition (AOTD), a parallel sequential quadratic programming (SQP) method for long-horizon nonlinear optimal control problems (OCPs). As designed, AOTD is the first overlapping temporal decomposition (OTD) algorithm that adapts the overlap size online, eliminating the need to fix a suitable overlap a priori. Specifically, at each iteration, it partitions the long horizon into overlapping nonlinear subproblems, performs one SQP step on each in parallel, and adaptively selects both the overlap size and the accuracy to which the resulting local KKT systems are solved. Two conditions govern the accepted step: an adaptive residual condition bounding the distance from the concatenated inexact direction to the exact Newton direction of the full problem, and a descent condition on the adaptive penalty parameters that certifies descent for a carefully chosen exact augmented Lagrangian. The residual condition is solver independent and accommodates both deterministic iterative solvers and randomized sketching solvers. Under standard regularity assumptions, we prove that the KKT residual converges to zero from any initialization and establish a local linear rate for sequences converging to a strict local minimizer. We validate AOTD on a power-system frequency regulation OCP and a Burgers PDE OCP, attaining a reduction in estimated FLOPs of approximately $2.5\times$ to the best fixed-overlap variant while converging across multiple horizon lengths with a single parameter setting.
Read the full abstract

Machine Learning

SMORE: Stability-Promoting Mesh-Agnostic Model Reduction for Time-Dependent PDEs

Yangyuan Li, Weichao Li and Shaowu Pan

High-fidelity simulations of time-dependent partial differential equations (PDEs) are computationally expensive, motivating data-driven reduced-order surrogates for many-query tasks such as uncertainty quantification, design optimization, data assimilation, and optimal control. However, existing surrogate models often exhibit poor temporal stability, which can lead to unstable rollouts and exploding gradients during backpropagation, especially in multistep long-horizon forecasting. To address this, we propose SMORE, a mesh-agnostic framework for model order reduction of time-dependent PDEs. Its latent dynamics are trained with Lyapunov-guided stability regularization, which promotes stable long-horizon rollouts. We provide theoretical guarantees under the stated structural assumptions. Beyond forecasting PDE evolution, the learned latent dynamics, which are interpretable and linear or linear-quadratic, could bring benefits for downstream tasks such as data assimilation and optimal control. Moreover, our framework is capable of predicting continuous PDE solution fields from sparse measurements of the initial condition. We evaluate SMORE on a range of problems, including wave propagation, the Navier-Stokes equations, and the shallow water equations. Our results show that it improves long-horizon rollout generalization and empirical robustness, and achieves competitive accuracy at comparable parameter budgets relative to competitive baselines including DINo, FNO, CNO, and Transolver.
Read the full abstract

Computation and Language

Turning Speech Language Models into Multilingual Listeners

Tolúlopé Ògúnrèmí, Dan Jurafsky, Chris Manning et al. (+2 more)

Speech Language Models (SLMs) that understand spoken language questions support only a few high-resource languages, limiting access to millions of people worldwide. This gap stems from the scarcity of multilingual speech instruction-tuning datasets. We present MULTISPEECHQA, a large-scale, synthetically generated and human-verified dataset comprising 9200 hours of 10.8 million spoken question-answer pairs in 23 typologically diverse languages. Using MULTISPEECHQA, we also introduce MULTISPEECH-BENCH, a multi-task benchmark for evaluating SLM performance on 23 languages. We compare the performance of a cascading system to open-weight and closed SLMs on MULTISPEECH-BENCH and find that the cascading system outperforms open-weight SLMs but not all closed SLMs. We use MULTISPEECHQA to finetune Qwen 2.5-Omni, which improves its performance on our benchmark. Our findings show that high-quality synthetic datasets offer a cheap solution to improving the multilingual capabilities of SLMs.
Read the full abstract

All authors Tolúlopé Ògúnrèmí, Dan Jurafsky, Chris Manning, Ahmet Üstün, Martijn Bartelds

Computer Vision

Structured Residual Connectivity Matters for Diffusion Transformers

Yuhe Liu, Xinyin Ma, Gongfan Fang et al. (+2 more)

Diffusion Transformers (DiTs) have established themselves as a scalable backbone for high-fidelity image synthesis. However, unlike U-Net based diffusion models that rely on rigid, hand-crafted skip connections, DiTs predominantly use a uniform residual stream that integrates all preceding layers as a monolithic state. In this work, we rethink residual connections in diffusion transformers and propose to transform them from passive summation into an active retrieval mechanism optimized for image denoising. First, we conduct a systematic analysis of DiT's internal representation, revealing a latent preference for early-layer feature reuse and symmetric layer guidance. Motivated by this, we introduce a structured connectivity design that explicitly integrates local residual connections with long-range pathways. Instead of static skip connections or dense all-layer routing, our method enables each transformer block to selectively “attend” to critical earlier representations, dynamically retrieving spatial and semantic cues through direct, differentiable cross-depth paths. Experiments show that our adaptive connectivity leads to faster convergence, with up to $1.73\times$ fewer training iterations, and significant gains in FID and visual quality with less than $0.1\%$ additional parameters, further improving a strong REPA-XL/2 model from $5.9$ to $4.34$ FID without guidance and reaching $1.39$ FID with classifier-free guidance. Our findings suggest that adaptive cross-layer connectivity is a critical yet underexplored factor in diffusion transformers, and that incorporating structured information pathways provides a simple and effective direction for improving scalable generative models.
Read the full abstract

All authors Yuhe Liu, Xinyin Ma, Gongfan Fang, Songhua Liu, Xinchao Wang

Computer Vision

ReAL: Accelerating Flow Matching through Segment Advancement with Shared Lookahead

Xuanhua Yin, Chuanzhi Xu, Haoxian Zhou et al. (+2 more)

Flow-matching models generate high-quality images and videos, but repeated neural network evaluations make sampling expensive. Skipping evaluations reduces this cost by extending an available velocity estimate over a longer span. However, local velocity agreement alone does not determine a suitable span, and checking each candidate endpoint adds costly model calls. We introduce ReAL, a training-free sampler that selects how far to advance using one shared lookahead. Our key insight is that the discrepancy between uncorrected and lookahead-corrected endpoint proposals can be computed directly from the observed velocity mismatch and the candidate span beyond the lookahead. This relation provides a span-dependent selection criterion without additional endpoint evaluations. The same lookahead selects the longest passing candidate span, corrects the accepted update, and supplies its velocity as the next starting estimate. After initialization, each regular iteration requires only one fresh evaluation. ReAL uses the pretrained velocity output and original noise schedule, with no additional training or access to internal features. Experiments cover four image-generation backbones, video generation, and image editing. ReAL achieves 4.91x measured speedup on FLUX.1-dev while retaining 97.0% of dense mean ImageReward. On HunyuanVideo, it achieves a 5.49x speedup while maintaining a VBench score close to that of dense sampling.
Read the full abstract

All authors Xuanhua Yin, Chuanzhi Xu, Haoxian Zhou, Shunqi Mao, Weidong Cai

Numerical Analysis

The stability barrier of a class of Hermite-type discretizations of advection equations

Xianyi Zeng

In this paper we fully categorize all hybrid-variable (HV) discretizations of linear advection equations according to their stability property and establish the stability barrier of these methods. In the HV discretization framework, we find numerical approximations to both cell-averaged solutions and nodal solutions and evolve them in time simultaneously. We prove that the HV methods have a similar stability barrier as the classical finite difference schemes, that the semi-discretized HV scheme is stable if and only if it uses a stencil such that the number of unknowns in the upwind direction is precisely that in the downwind direction plus one or two, with only one exception when the two numbers are three and zero, respectively. It is also proved that all central HV schemes are neutrally stable, in the sense that the L2-norm of the solution remain uniformly bounded at all times. The theoretical predictions are verify by extensive numerical tests.
Read the full abstract

Machine Learning

Teach Yourself Where to Look: On-Policy Attention Self-Distillation for Reasoning

Safaeid Hossain Arib, Rabeya Akter, Ismam Nur Swapnil et al. (+3 more)

On-policy self-distillation trains reasoning models on their own trajectories using dense token distribution guidance from a privileged teacher with access to a verified solution. This supervision transfers what the teacher predicts without directly transferring where it attends within the preceding context. We introduce On-Policy Attention Self-Distillation (OPASD), which complements token-level supervision with solution-conditioned attention distillation. Because the privileged teacher can attend to verified solution tokens unavailable to the student, OPASD projects teacher attention onto student-visible positions and renormalizes the resulting distribution before alignment. Across three model sizes and four competition-level mathematics benchmarks, OPASD consistently outperforms token-only OPSD, improving average accuracy by 4.98 to 8.40 percentage points. OPASD also avoids the response-length inflation and performance degradation observed with token-only distillation, reducing generated rollout tokens by 73.9% and estimated model compute by 72.6% while training 1.53x faster. These results show that solution-conditioned attention provides a complementary supervision signal that makes on-policy self-distillation more accurate, stable, and compute-efficient.
Read the full abstract

All authors Safaeid Hossain Arib, Rabeya Akter, Ismam Nur Swapnil, Md. Faiyaz Abdullah Sayeedi, Tasnim Mohiuddin, Md Mofijul Islam

Robotics

TAO-DA: Towards Autonomous Operation–A Dual-Arm Vision-Language-Action Model for Coordinated Manipulation

Yongsheng Zhao, Han Gao, Baoping Cheng et al. (+7 more)

Vision-Language-Action (VLA) models provide a unified framework for grounding high-level semantic information into low-level robot actions, enabling scalable robotic manipulation across diverse tasks. However, existing VLA models lack explicit mechanisms to disentangle the states and intents of the two arms, leading to unintended cross-arm interference that degrades task execution success. To address this issue, we propose a symmetric Dual-Arm Expert (DAE) architecture built upon a shared Vision-Language Model (VLM) backbone with decoupled, arm-specific expert towers. Expert selection is carried out through a two-stage dual-arm intent routing scheme, in which experts are routed either by explicit language instructions in the first stage or by implicit visual semantics in the second stage. Moreover, we introduce a lightweight task progress prediction module that leverages cross-attention between the pre-chunk temporal features and semantic representations of proprioceptive and visual observations to accurately estimate frame-wise task completion progress. This module facilitates task progress synchronization to support coordinated scheduling for collaborative multi-robot tasks. Experimental results demonstrate the effectiveness of our model in dual-arm intent routing and the disentanglement of cross-arm interference, and further provide preliminary evidence of emergent skill generalization from single- to dual-arm tasks (as well as the reverse), together with cross-arm motion-domain skill transfer.
Read the full abstract

All authors Yongsheng Zhao, Han Gao, Baoping Cheng, Jingyao Tang, Dian Zhou, Deng Liang, Ji Ge, Xuanzhang Wen, Lei Zhao, Ye Wang

Artificial Intelligence

Are Benchmarks Reliable? Toward Structural Diagnosis via Item-Level Capability Boundaries

Haiquan Hu, Yuzhu Liang, Weicheng Tang et al. (+4 more)

Evaluating large language models (LLMs) relies heavily on benchmark scores, yet aggregate metrics can obscure whether individual items serve their intended measurement purpose. BSDProbe provides an item-level framework for benchmark structural diagnosis that jointly characterizes correctness transitions and their supporting response evidence. Repeated responses along an empirically ordered model axis yield complementary correctness and normalized entropy trajectories, from which four-dimensional profiles of boundary position, boundary width, boundary-signal validity, and order consistency are constructed for benchmark-level aggregation. Experiments on six benchmarks identify varying proportions of potentially anomalous items. With Qwen3 as both the selection and reference axis, BSDProbe achieves a 17.9% mean relative improvement in normalized discrimination ratio over the best baseline per benchmark and matches or exceeds all baselines in ranking agreement with the full benchmark.
Read the full abstract

All authors Haiquan Hu, Yuzhu Liang, Weicheng Tang, Yanzeng Li, Yao Shi, Li Xu, Tian Wang

Multimedia

ReVR: Dual-Path Concept Reasoning for Multimodal Fake News Detection

Zhikai Tan, Yuzhou Yang, Qichao Ying et al. (+4 more)

Vision-language models (VLMs) support multimodal fake news detection (FND) by producing explicit analyses. Recent methods further improve interpretability by organizing verification knowledge into explicit concepts. However, two questions remain: how to improve the reliability and applicability of verification concepts, and how to effectively apply reusable concepts to verify unseen news. We propose ReVR, a dual-path reasoning framework that constructs and applies reusable verification concepts for multimodal fake news detection. An agentic workflow grounds and consolidates candidate concepts, while statistical profiles characterize their historical behavior. During inference, a coverage-oriented path aggregates evidence from the complete concept library using a trainable encoder, while a query-focused path prompts a frozen VLM to reason over selected concepts and their observations. A learned conflict resolver selects between the two predictions when they disagree. Experiments on fake news benchmarks demonstrate the effectiveness of the method regarding detection performance and generalizability.
Read the full abstract

All authors Zhikai Tan, Yuzhou Yang, Qichao Ying, Pinjie Xu, Sheng Li, Zhenxing Qian, Xinpeng Zhang

Machine Learning

Orthogonal Witness Control for Muon Optimization via Sigmoid Spectral Reshaping

Dat Phi Van, Ngo Vu Minh, Tuc Nguyen et al. (+3 more)

Matrix-valued optimizers such as Muon exploit the spectral structure of neural network updates through Newton–Schulz orthogonalization, but their near-flattening of the singular spectrum discards relative magnitude information across gradient modes. We introduce Soren (Spectral Orthogonal Reshaping), a matrix-valued optimizer that preserves the singular subspaces of the gradient while applying a bounded, monotone sigmoid transformation to its singular values. This smoothly compresses dominant modes without fully flattening the spectrum. We interpret Soren as a positive-definite preconditioned gradient method and establish convergence guarantees under relative smoothness and metric Polyak–Łojasiewicz geometry. To avoid explicit singular value decomposition, we further develop a finite-depth Soft Newton–Schulz (SNS) polynomial realization of the sigmoid spectral map and characterize how its spectral approximation affects the induced convergence geometry. Experiments across LLM pre-training, supervised fine-tuning, and direct preference optimization demonstrate the effectiveness and robustness of Soren against established optimizers.
Read the full abstract

All authors Dat Phi Van, Ngo Vu Minh, Tuc Nguyen, Thin Nguyen, Ngoc-Thanh Dinh, Trung Le

Machine Learning

Apparent Compression, Real Stability: The Intrinsic Dimension of Learning a Quantum Wavefunction

Lu Wei, Yufeng Wang, Chenfeng Cao et al. (+1 more)

How many directions in weight space does training need? The intrinsic dimension answers this with the smallest number of random directions in which training still reaches a target accuracy, and small values have motivated parameter-efficient methods such as LoRA. We measure it for variational Monte Carlo (VMC), which trains a neural network to represent the ground state of a quantum many-body system. VMC is a demanding test, because the network generates its own training samples and every gradient is noisy, and a revealing one, because the exact answer is known and every run can be scored. We train only a small latent vector that a frozen random map turns into the network's weights, with no change to the standard natural-gradient optimizer. We find that a small dimension can be misleading, while the stability it brings is real. On a magnet with a hard sign pattern, a network that cannot represent signs reaches its best energy in 8 of 28,642 directions, but only because no such network can go lower; once signs are learnable, neither the signs nor the magnitudes are cheap. The dimension rises across a quantum phase transition, so it tracks how difficult a state is at far less compute than fitting a scaling law, yet it never falls below a floor set by the random subspace itself, even where the ground state is nearly trivial. Training in the subspace, in contrast, never diverged in our experiments, whereas full-parameter training with the same settings did, and a control with matched solvers attributes the difference to the reduced dimension.
Read the full abstract

All authors Lu Wei, Yufeng Wang, Chenfeng Cao, Haibin Ling

Machine Learning

AG-CoT: Verified Algorithmic Traces for LLM Program Synthesis on Clifford Circuits

Lu Wei, Yufeng Wang, Chenfeng Cao et al. (+2 more)

Scientific code generation can produce executable programs that fail to compute the intended scientific object. We study this problem in language-model synthesis of Clifford circuits, which prepare the stabilizer states used in quantum error correction and admit exact classical verification. In our target-conditioned framework, each target is given as compact signed stabilizer generators, and an exact verifier checks the generated OpenQASM circuits. We supervise models with Aaronson-Gottesman chain-of-thought (AG-CoT) traces checked by the verifier, and continue training on model generations that the verifier accepts. Across two independently trained model families (3B and 7B), AG-CoT supervision multiplies greedy-decode state-equivalence accuracy by four to six times over circuit-only baselines, and verifier-filtered continuation training adds a further consistent gain atop both. A complementary 32B study shows that supervised models achieve near-perfect syntax and Clifford validity while the strongest direct model reaches 6.14% state equivalence per target, rising to over 10% under verifier-guided selection with multiple candidates. These results show that algorithmic trace supervision gives a large, statistically significant gain in both model families and that verifier-filtered continuation adds a further repeated gain. The persistent gap between Clifford validity and state equivalence confirms that exact verification is necessary: a circuit can be syntactically and physically valid yet prepare the wrong quantum state.
Read the full abstract

All authors Lu Wei, Yufeng Wang, Chenfeng Cao, Lu Pang, Haibin Ling

Computer Vision

FocusDrive: Reasoning with Visual Focus for Autonomous Driving

Zhiyuan Liu, Zehong Ke, Yuanxin Tian et al. (+7 more)

Driving decisions depend on both where to focus and how to act on what is seen. Effective driving reasoning must establish which objects matter, where they are, and how they inform the intended action. Text-based rationales can describe a driving response while leaving its correspondence to specific visual evidence implicit. Visual focus provides a concrete starting point for this connection by identifying what matters in the scene and where it is. We propose FocusDrive, a structured multimodal reasoning framework that organizes end-to-end planning around explicit visual focus. It pairs descriptions of decision-relevant objects with image-patch references, bringing explicit visual focus into the reasoning that generates driving plans and trajectories. We first assess this focus representation through driver gaze prediction, then investigate its role in planning reasoning using driving-focus annotations within existing NAVSIM training scenes. Experiments on W3DA and NAVSIM demonstrate competitive gaze prediction and end-to-end planning performance, with FocusDrive improving over text-based chain-of-thought. These results support visual focus as an effective link between scene understanding and driving action.
Read the full abstract

All authors Zhiyuan Liu, Zehong Ke, Yuanxin Tian, Hao Cheng, Jinhao Li, Yining Xing, Yanbo Jiang, Zhenhua Xu, Wenhao Yu, Jianqiang Wang

Machine Learning

When an Evaluation Rule Writes Training Labels: Measuring Human-Reference Forgiveness in NAVSIM

Jiaxuan Guo, Jingxin Yang, Jiaqi Ye et al. (+4 more)

When the human reference scores zero on a metric, the released GTRS-Dense label generator for NAVSIM marks every candidate trajectory in the scene as passing it. NAVSIM's authors introduced this human-reference forgiveness to avoid penalizing contextually justified maneuvers when scoring one trajectory, and warned that it could overlook important failures. In label generation it sets a whole column of 16,384 candidate targets to passing. To measure the consequences for supervision, we re-run the generator with the overwrite disabled and compare the pre-overwrite targets with the released labels on all 103,288 navtrain scenes. The rule erases a candidate distinction that the training loss reads on 11,237 of them (10.8793%). Firing usually changes most of a column: lane keeping carries 9,982 of the 13,042 forgiven loss columns, and its median forgiven column had 14,391 of 16,384 candidates failing before the overwrite. On held-out navtest scenes forgiven on lane keeping, the released lane-keeping head's median AUC against the pre-overwrite outcome is 0.7095; on unforgiven scenes matched on failing-candidate count it is 0.9807. For the Hydra-MDP checkpoint released with GTRS, whose configuration takes the same label file, the two values are 0.6627 and 0.9761. Continuing the released GTRS-Dense checkpoint for 300 optimizer steps with three paired seeds, we observe the forgiven-scene AUC 0.1086-0.1251 higher with pre-overwrite than with published targets, and a narrower gap between matched groups, still above zero. Scoring with forgiveness disabled, we observe lane keeping higher by 2.478-3.524 points on navtest scenes forgiven on any of five loss metrics, with lower adjacent-frame plan consistency. Both changes are larger there than on the rest. EPDMS, scored the same way, does not separate the two target sets.
Read the full abstract

All authors Jiaxuan Guo, Jingxin Yang, Jiaqi Ye, Youran Sun, Shuo Xin, Kejia Zhang, Haizhao Yang

Machine Learning · Cross-listed from stat.ML

Offline Policy Evaluation via Mixed Bellman Residuals and Adaptive Critic Representations

Amitakshar Biswas, Yuhan Li and Ruoqing Zhu

Evaluating a target policy using data generated by a different behavior policy remains a fundamental challenge in reinforcement learning. While most existing work relies on the standard one-step Bellman residual, we consider a convex combination of one-step and two-step residuals with a fixed mixing weight. In ideal settings, this mixed Bellman formulation can provide a natural bias–variance trade-off between approximation error under a restricted value-function class and the increased variance arising from multi-step importance weighting. To solve this mixed residual optimization, we adopt a minimax formulation involving a critic function. Unlike standard approaches that rely on a fixed functional class, we construct a data-dependent critic representation using predicted future feature directions which effectively induces a kernel adapted to the underlying transition dynamics. This allows the critic to focus on directions that are most relevant for the estimated Bellman error. To control overfitting, we use sample splitting to construct the critic and estimate the value function on separate data subsets. Simulation studies and MetaWorld tasks illustrate the effect of the mixing parameter and show that intermediate residual combinations can improve value estimation in challenging settings.
Read the full abstract

Hardware Architecture

Resource-Efficient Speculative Decoding for Long-Context LLM Serving

Fei Li, Song Liu, Shiqiang Nie et al. (+2 more)

Speculative decoding reduces sequential Target model calls by verifying multiple tokens from the Draft model in parallel. Yet KV Cache growth limits long-context serving under constrained GPU memory. Offloading KV to CPU memory relieves this pressure. However, existing offloading schemes restore the full KV history before attention and fail to fully exploit the benefits of KV sharing across queries within a verification round. Existing parallel speculative decoding methods also overlook idle GPU compute capacity while memory-bandwidth-bound Target verification waits for historical KV. We present SpecStream, a speculative decoding system that begins verification without waiting for the full KV history to be restored and exploits compute bubbles during KV transfers for concurrent drafting on the same GPUs. It offloads only Target-committed history, keeping candidate rollback local to the GPUs. Each streamed KV chunk serves all queries in the round, with online softmax preserving full attention. Target-priority scheduling controls Draft concurrent execution under resource limits to constrain interference with Target verification. Experiments show that SpecStream maintains task quality close to SGLang speculative decoding while supporting more concurrent requests under limited GPU memory. Across different datasets, it achieves average throughput speedups of 1.41$\times$ and 1.32$\times$ over the offloading baseline for Qwen3 and InternLM2.5, respectively. Compared with parallel speculative decoding on separate Target and Draft GPUs, SpecStream improves output throughput per GPU by an average of 55.4%.
Read the full abstract

All authors Fei Li, Song Liu, Shiqiang Nie, Jinyu Wang, Weiguo Wu

Computation and Language

Identifying Temporal Features within Transcoders for Time Sensitive Factual Recall

Sanjay Govindan, Yang Song and Maurice Pagnucco

Large Language Models (LLMs) suffer from temporal misalignment, often due to the contradictory nature of their training corpora. While current mitigation strategies rely on computationally expensive fine-tuning or context-heavy retrieval augmented generation (RAG), the internal mechanisms governing time-sensitive recall remain under-explored. Unlike prior studies that identify temporal components such as attention heads and MLP layers, we provide the first feature-level map of temporal recall by isolating individual MLP features via transcoder circuit tracing. We identify three node categories (common temporal, common to the year, and chrono-semantic) which interact to generate a temporal filter during factual recall. By analysing Gemma 2 2B, LLaMA 3.2 1B, and Qwen3-4B, we show that these features do not follow a simple linear pipeline but represent time through a parallel and mixed syntactic-semantic interplay across layers. We additionally discover a class of higher-layer temporal components invisible to existing EAP-IG methods, establishing transcoders as a more complete lens for temporal interpretability in time-sensitive factual recall. These findings present MLP components for potential targeted interventions in time-sensitive factual recall
Read the full abstract

Artificial Intelligence

Unlocking Latent Personalization in LLMs

Wei Chen, Guanghui Zhu, Zhongliang Cai et al. (+1 more)

Large language models (LLMs) are increasingly expected to adapt to individual users, yet effective personalization remains challenging when only limited user-specific samples are available. In this work, we take an alternative perspective: pretrained LLMs may already possess latent capacity for personalization, and a few user samples may therefore suffice to guide the model toward user-aligned behavior with minimal user-specific adaptation. From this perspective, we propose LatentPersonal, a framework that formulates personalization as navigation in a shared latent adaptation space. LatentPersonal infers a compact latent representation from a few user samples to guide user-specific model adaptation, regularized with a variational information bottleneck to encourage compact preference representations. We instantiate LatentPersonal with LoRA, leveraging its low-rank parameterization as a natural low-dimensional adaptation space for personalization. By simply inserting a user-specific guidance vector between the shared low-rank factors, the model can navigate toward personalized adaptations through lightweight inference of this compact representation, without updating the shared LoRA parameters. Experiments across multiple personalization datasets demonstrate that LatentPersonal substantially reduces user-specific adaptation overhead while achieving effective personalization from only a few user-specific interactions, with particularly strong performance in the one-shot regime.
Read the full abstract

All authors Wei Chen, Guanghui Zhu, Zhongliang Cai, Yihua Huang

Artificial Intelligence

SeOPD: Self-Evolving LLMs via Online Policy Distillation from Self-Generated Chain-of-Thought

Xiaoshu Chen, Sihang Zhou, Ke Liang et al. (+1 more)

Recent advances in online policy self-distillation (OPSD) have demonstrated that large language models (LLMs) can improve their capabilities by leveraging external privileged information (PI), such as manual annotations or feedback from external environments. However, obtaining accurate annotations and constructing sophisticated environments often require substantial human effort and computation, limiting the scalability of OPSD. While a few recent studies have explored self-improvement without external PI, the resulting gains remain limited. In this work, we explore whether LLMs can achieve comparable self-improvement without external PI. Our key observation is that a single LLM can support multiple reasoning modes, such as deep-thinking and non-thinking modes, with deep thinking generating additional information during reasoning. Based on this observation, we propose Self-Evolving Online Policy Distillation (SeOPD), which enables LLMs to distill and internalize information generated by their own chain of thought (CoT). Specifically, it (1) generates CoT with the deep-thinking mode, (2) produces responses with the non-thinking mode, and (3) uses the generated CoT as PI to provide token-level supervision for the non-thinking response, allowing new information inferred during reasoning to guide the non-thinking mode and be internalized into the shared model parameters, thereby improving both non-thinking and deep-thinking capabilities. Extensive experiments across LLMs and tasks demonstrate the effectiveness of SeOPD.
Read the full abstract

All authors Xiaoshu Chen, Sihang Zhou, Ke Liang, Xinwang Liu