Vision-Language-Action (VLA) models show strong generalization for robotic control, but finetuning them with reinforcement learning (RL) is constrained by the high cost and safety risks of real-world interaction. Training VLA models in interactive world models avoids these issues but introduces several challenges, including pixel-level world modeling, multi-view consistency, and compounding errors under sparse rewards. Building on recent advances across large multimodal models and model-based RL, we propose VLA-MBPO, a practical framework to tackle these problems in VLA finetuning. Our approach has three key design choices: (i) adapting unified multimodal models (UMMs) for data-efficient world modeling; (ii) an interleaved view decoding mechanism to enforce multi-view consistency; and (iii) chunk-level branched rollout to mitigate error compounding. Theoretical analysis and experiments across simulation and real-world tasks demonstrate that VLA-MBPO significantly improves policy performance and sample efficiency. Crucially, our method maintains a universal set of hyperparameters across all tasks, underscoring its robustness and scalability for real-world robotic deployment.
论文检索
输入标题、作者或关键词，从 13,033 篇学术成果中精准定位
Deep Learning · Large Language Models
AI Scientists have shown promising progress across multiple stages of the research pipeline, among which automatic scientific paper writing remains a formidable challenge. The Introduction writing is especially challenging, which demands not only linguistic fluency, but logical soundness and verifiable faithfulness. Most AI-assisted methods treat the task as text generation instead of reasoning and structuring, leading to severe drawbacks, e.g., hallucinating citations. To address this, we first formulate the Content-Conditional Introduction Generation (CCIG) task, which requires grounding the Introduction in the paper's core evidence. We then propose LECTOR, a novel Logic-Expression Co-Reinforcement Learning framework that can strictly follow the scientist's logic, add high-quality citations and keep structured expressions. LECTOR first constructs a logic-reasoning graph from the paper's main body to serve as a verifiable logical blueprint. Subsequently, it employs a Logic-Expression Co-Rewarding mechanism to jointly optimize for both the graph's structural fidelity and the final narrative's quality. We conduct a dataset from Nature Communications papers to assess our method. Extensive experiments show consistent improvements in both logic fidelity and Introduction generation quality metrics, e.g., Graph Quality (+26.7%), Citation Quality (+8.6%), and Paper Consistency (+3.3%). The datasets, code, and pretrained models shall be released.
Deep Learning · Generative Models and Autoencoders
Test-time guidance is a widely used mechanism for steering pre-trained diffusion models toward outcomes specified by a reward function. Existing approaches, however, focus on reward maximization rather than sampling from the true Bayesian posterior, leading to miscalibrated inference. In this work, we show that common test-time guidance methods do not recover the correct posterior distribution and identify the structural approximations responsible for this failure. We then propose consistent alternative estimators that enable calibrated sampling from the Bayesian posterior. Across Bayesian inference and inverse problems, our approach yields substantially improved posterior calibration.
Applications · Computer Vision
Wireless channel modeling is essential for the design, analysis, and optimization of modern wireless sensing and communication systems. However, accurately modeling wireless channels in electrically large and complex environments remains a long-standing challenge, owing to the intricate interactions between radio-frequency (RF) signals and surrounding objects (e.g., reflection, diffraction, and scattering). Unlike conventional ray-tracing pipelines that rely on hand-engineer interaction rules, or black-box neural surrogates that do not explicitly model physical structure, we introduce SNRFT, a novel framework that integrates neural representations with physics-based RF propagation modeling. Our key idea is to view RF transport as a stochastic propagation process, from which a material-dependent attenuation coefficient emerges naturally as the rate parameter governing transport dynamics. This formulation inherently satisfies key physical constraints such as reciprocity and reversibility. Building on this foundation, we employ implicit neural representations to capture complex RF-object interactions while preserving the composability of traditional ray tracing. Extensive evaluations on real-world wireless communication and sensing testbeds demonstrate that SNRFT consistently outperforms existing methods, while requiring significantly fewer training samples.
Applications · Chemistry, Physics, and Earth Sciences
Simulation-Based Inference (SBI) is critical for scientific discovery, with generative models offering a promising path toward efficient inference. However, existing methods struggle with effective multimodal modeling. They often rely on brute-force fusion strategies that ignore the structural disparities between parameters and observations, thus limiting estimation fidelity. In this work, we introduce FUSE (Feynman-Kac steered mUlti-modal flow matching for efficient Simulation-based posterior Estimation). Unlike prior work, FUSE employs a dual-track architecture that preserves the distinct features of multimodal inputs while facilitating dynamic interaction. Additionally, we propose an FK-steered sampling strategy that leverages intermediate observation likelihoods to guide the generative trajectories, effectively improving the sample quality during inference. Our approach outperforms state-of-the-art baselines on standard SBI benchmarks, producing posteriors that closely match ground-truth MCMC. Furthermore, in a real-world exoplanet orbital estimation task, FUSE successfully resolves complex parameter degeneracies that challenge existing methods, highlighting its potential to accelerate complex scientific discoveries in astrophysics and beyond.
General Machine Learning · Representation Learning
Whether deep vision models recognize objects primarily by shape or texture remains a central and unresolved question in computer vision. Early studies report a strong texture bias in convolutional neural networks (CNNs), while other work reports shape-biased representations. We argue that much of this apparent discrepancy reflects methodological confounds and a conflation of local contour sensitivity with genuine global shape understanding. Using minimal, tightly controlled stimuli, we directly compare cue-conflict and cue-suppression paradigms within a unified experimental framework. We show that standard CNNs consistently prioritize texture over global shape when cues compete, even when shape information is explicitly available. Evidence for shape bias typically reflects reliance on local fragments rather than invariant, relational representations of object structure. Our findings support the view that texture bias is fundamentally rooted in architectural inductive biases rather than data or optimization alone. This gap has direct consequences for robustness, safety, and generalization, and motivates the development of architectures that explicitly support global integration and relational reasoning, moving beyond incremental data-driven fixes.
Deep Learning · Large Language Models
Supervised fine-tuning (SFT) on a small high-quality set of long reasoning traces is an effective way to enable strong reasoning abilities for Large Language Models (LLMs). However, curating a high-quality SFT data requires generating a large pool of long Chain of Thoughts (CoTs), and filtering the generated data for diversity and difficulty. Both stages rely heavily on strong reasoning models and make data curation prohibitively expensive. In this work, we show that diverse and difficult reasoning examples can be identified very early during their generation. We show that after generating as few as 100 out of 34k tokens of a reasoning trace, challenging examples can be reliably identified based on their loss at a highly perturbed checkpoints of the pretrained model. Then, we prove that examples with similar loss trajectory, i.e., value at a few noisy, perturbed checkpoints of the pretrained model, have similar gradients. A diverse subset can be then found by sampling from clusters of loss trajectories obtained after generating 1k tokens. Our extensive experiments for fine-tuning Qwen2.5-7B and Llama3 on m23K medical reasoning and Openthoughs datasets confirms the effectiveness of our approach. our approach outperforms existing baselines by up to 2\% while generating only as few as 9\% tokens for reasoning traces.
Existing definitions of agent security are ambiguous because they do not fully capture the holistic view across agent components. For instance, current work fails to distinguish between potentially legitimate administrative tasks and malicious exploitation of the same command. A command to "delete user data" could be either instruction following to reset a sandbox or a prompt injection attacking production systems. We argue that agent security must be redefined through a holistic framework including four core components: identity (who: authority and authentication), task (what to do: authorized objectives), trajectory (progress: action-observation boundaries), and memory (what can be retrieved: information access control). Our framework redefines existing security violations (e.g., reframing prompt injection as an identity violation), enables discovery of new attack vectors, and distinguishes legitimate capabilities like instruction following from security violations like prompt injection attacks. Critically, we demonstrate that temporal aspects are essential: attacks can be misdefined or unnoticed without accounting for how security components in our framework evolve over time. Our framework further identifies that agentic task decomposition and data and control flow patterns are crucial to rigorous security definitions, aspects previous frameworks fail to address, and provides a new foundation for future agent security work.
General Machine Learning · Supervised Learning
Quadratic Discriminant Analysis (QDA) assumes Gaussian class-conditional distributions, causing systematic misclassification when data exhibit heavy tails. We propose Stable-QDA, which replaces the Gaussian likelihood with a symmetric $\alpha$-stable likelihood that decays polynomially rather than exponentially in Mahalanobis distance. Crucially, we find that correcting likelihood misspecification yields larger gains than robustifying parameter estimation: standard estimators (sample mean, Ledoit--Wolf covariance) often outperform robust alternatives when class heteroscedasticity is discriminative. We provide consistency guarantees under infinite-variance regimes, data-driven diagnostics for estimator selection, and demonstrate 15--53\% error reduction on real-world heavy-tailed benchmarks.
Deep Learning · Generative Models and Autoencoders
Multimodal generative models require a unified approach to handle both discrete data (e.g., text and code) and continuous data (e.g., image, audio, video). In this work, we propose Latent Language Modeling (LatentLM), which seamlessly integrates continuous and discrete data using causal Transformers. Specifically, we employ a variational autoencoder (VAE) to represent continuous data as latent vectors and introduce next-token diffusion for autoregressive generation of these vectors. Additionally, we develop -VAE to address the challenges of variance collapse, which is crucial for autoregressive modeling. Extensive experiments demonstrate the effectiveness of LatentLM across various modalities. In image generation, LatentLM surpasses Diffusion Transformers in both performance and scalability. When integrated into multimodal large language models, LatentLM provides a general-purpose interface that unifies multimodal generation and understanding. Experimental results show that LatentLM achieves favorable performance compared to Transfusion and vector quantized models in the setting of scaling up training tokens. In text-to-speech synthesis, LatentLM outperforms the state-of-the-art VALL-E 2 model in speaker similarity and robustness, while requiring 10 fewer decoding steps. The results establish LatentLM as a highly effective and scalable approach to advance large multimodal models.
Deep Learning · Sequential Models, Time series
We argue that long-term forecasting requires learning local Jacobians with explicit spectral structure, going beyond simple conditional mean matching. Our method, \textsc{Fern}, invokes Brenier's theorem to directly parameterize the Jacobian as a symmetric positive semi-definite (SPD) factorization, treating forecasting as the optimal transport of probability mass from a fixed Gaussian source to data-dependent ellipsoids. This formulation reduces the computational cost of eigen-decomposition from cubic to linear time while providing interpretable, geometry-aware projections. To rigorously evaluate robustness, we introduce a synthetic benchmark with controlled non-stationary shocks alongside new metrics like Effective Prediction Time (EPT). \textsc{Fern} demonstrates exceptional stability, outperforming baselines like DLinear and Koopa by over two orders of magnitude (up to $790\times$) on nonstationary settings where standard benchmarks fail to expose model brittleness.
Applications · Neuroscience, Cognitive Science
Spiking Neural Networks (SNNs) have garnered increasing attention for their biological plausibility, energy efficiency, and temporal modeling capability. Due to the non-differentiability of spike generation, a widely used supervised training method for SNNs is backpropagation through time with surrogate gradients, which achieves competitive performance with a small number of timesteps. Intuitively, scaling timesteps should further improve performance by enriching temporal dynamics. However, we observe timestep scaling paradox (TSP), a counter-intuitive degradation in accuracy when scaling timesteps. We investigate TSP and link it to long-term temporal gradient vanishing and weakened cross-timestep dependencies. To address this, we propose the Timestep-Scalable (TS) neuron model. It introduces long-term memory reconsolidation to enhance cross-timestep information flow and enable effective learning with more timesteps. In parallel, a temporal forgetting mechanism periodically truncates the accumulation path, suppressing excessive temporal information buildup and improving training stability. Supported by theoretical analysis and extensive experiments, TS consistently improves performance when scaling timesteps. Beyond gains from timestep scaling, it attains state-of-the-art results on EEG signals, event-based recognition, and time-series forecasting, while remaining strong on conventional image classification and object detection datasets.
Deep Learning · Large Language Models
Recent work asks whether large language models (LLMs) condition their reasoning on explicit rules rather than statistical regularities from pretraining. Program execution provides a canonical instance: formal semantics define behavior through symbolic transition rules that can be systematically altered under distribution shift. We investigate whether LLMs can condition their reasoning on formal semantics through program execution and introduce PLSemanticsBench, pairing featherweight C programs with two semantic systems—small-step operational semantics and K semantics—and probing four capabilities: composing rules for final states, selecting rules when state is unmutated, sustaining such conditioning over long traces, and following supplied rules under novel semantics. To decouple semantic reasoning from syntactic familiarity, we redefine familiar operators to induce symbol-meaning conflict and introduce novel symbols defined only through the supplied rules, and stress-test models on Human-Written, LLM-Translated, and Fuzzer-Generated splits with increasing structural complexity. Across 11 frontier LLMs, strong final-state accuracy under standard semantics (up to 90%) drops sharply—by as much as 40–60% points—under semantic mutations and increasing structural complexity. Only a handful of models achieve non-zero long-horizon conditioning accuracy, and even the best systems reach just 35%. Together, these results suggest that contemporary LLMs often rely on pretrained lexical associations rather than systematically conditioning on supplied formal rules. PLSemanticsBench is publicly available at https://EngineeringSoftware.github.io/PLSemanticsBench.
Social Aspects · Accountability, Transparency, and Interpretability
AI models readily refuse explicitly unlawful requests, but real-world illegality often depends on context. We evaluate frontier models on contextual illegality across four corporate law domains in which routine actions—editing documents, trading stock, requesting payment, approving communications—become unlawful due to triggers such as pending investigations or bankruptcy filings. We study both chat and agentic settings and compare results to a human baseline. The best-performing models achieved near-zero compliance with illegal requests while maintaining high compliance with legal ones, though performance varied sharply by domain. We also identify distinct failure modes such as excessive refusal of legal requests and find improved performance from reasoning models and agentic environments. By utilizing the structure of contextual illegality to create controlled evaluations, our methodology provides empirical grounding for emerging research on law-following AI and extends naturally to additional legal domains.
We study multi-objective optimization over probability distributions in Wasserstein space. Recently, \citet{nguyen2025multiple} introduced Multiple Wasserstein Gradient Descent (MWGraD) algorithm, which exploits the geometric structure of Wasserstein space to jointly optimize multiple objectives. Building on this approach, we propose an accelerated variant, A-MWGraD, inspired by Nesterov's acceleration. We analyze the continuous-time dynamics and establish convergence to weakly Pareto optimal points in probability space. Our theoretical results show that A-MWGraD achieves a convergence rate of $\mathcal{O}(1/t^2)$ for geodesically convex objectives and $\mathcal{O}(e^{-\sqrt{\beta}t})$ for $\beta$-strongly geodesically convex objectives, improving upon the $\mathcal{O}(1/t)$ rate of MWGraD in the geodesically convex setting. We further introduce a practical kernel-based discretization for A-MWGraD and demonstrate through numerical experiments that it consistently outperforms MWGraD in convergence speed and sampling efficiency on multi-target sampling tasks.
Applications · Robotics
Vision–Language–Action (VLA) models enable general-purpose robotic control via large-scale multimodal pretraining, yet their effectiveness under few-shot imitation learning remains limited. We conduct a systematic stress test of state-of-the-art VLA models and show that performance degrades sharply as demonstrations are reduced, revealing a key weakness of existing adaptation strategies. To address this, we introduce FOCA, a future-oriented conditioning framework for data-efficient VLA adaptation. FOCA combines explicit prediction of task-grounded future interaction embeddings with implicit alignment to future goal observations, enabling long-horizon reasoning in latent space without pixel-level prediction. This formulation naturally supports action-free co-training with synthetic videos from video world models and can be interpreted as learning a future-conditioned value-like representation. Extensive experiments demonstrate FOCA achieves 95.7\% success with 20 demonstrations on LIBERO, improves 7–12\% on RoboCasa, and delivers up to 26\% absolute gains on real robots, establishing a new state of the art in few-shot VLA adaptation.
Theory · Learning Theory
Continual learning, the ability of a model to adapt to an ongoing sequence of tasks without forgetting earlier ones, is a central goal of artificial intelligence. To better understand its underlying mechanisms, we study the limitations of continual learning in a tractable yet representative setting. Specifically, we analyze one-hidden-layer quadratic neural networks trained by gradient descent on a sequence of XOR-cluster datasets with Gaussian noise, where different tasks correspond to clusters with orthogonal means. Our analysis is based on a tight characterization of gradient descent dynamics for the training loss, which yields explicit bounds on the rate of train-time forgetting as functions of the number of iterations, sample size, number of tasks, and hidden-layer width. We then leverage an algorithmic stability framework to bound the generalization gap, leading to corresponding guarantees on test-time forgetting. Together, our results provide the first closed-form guarantees for forgetting in continual learning with neural networks and show how key problem parameters jointly govern forgetting dynamics. Numerical experiments corroborate our theoretical results.
Deep Learning · Large Language Models
The annealing stage of Large Language Model (LLM) training is a critical phase where model loss drops sharply and downstream capabilities solidify. Despite its importance, current practices rely on empirical heuristics like quality filtering or context extension, lacking a principled understanding of the underlying optimization dynamics. We address this gap by providing a theoretical characterization of the spectral properties targeted during annealing. We demonstrate that effective annealing requires balancing global Hessian geometry with sample-wise gradient noise, navigating a landscape of highly anisotropic curvature. Based on these insights, we formulate sample selection as a constrained optimization problem to suppress noise in sharp directions while preserving descent signals in flat subspaces. Our method, solved via Successive Convex Programming (SCP), achieves state-of-the-art results across multiple model scales. Code is available at \url{https://anonymous.4open.science/r/LLM-Annealing-Phase}.
Deep Learning · Large Language Models
Training data plays a central role in large language model (LLM) optimization, motivating extensive research on data scheduling strategies. Most prior work focuses on data selection and implicitly assumes that, once the training subset is fixed, the order in which data are presented is interchangeable. However, this assumption is routinely violated in practice. Despite empirical evidence of order sensitivity, existing studies neither provide a principled explanation of the underlying optimization dynamics nor offer an efficient solution. In this work, we first answer the fundamental question of why training order matters in LLM optimization. We then demonstrate that commonly used empirical data ordering heuristics are suboptimal from an optimization perspective. To resolve this, we propose xxx, a data scheduling framework grounded in gradient interactions between samples, where training dependencies are modeled as a graph that explicitly constrains valid training orders. Our approach is theoretically motivated and yields consistent empirical improvements over existing data scheduling methods across multiple settings.
Applications · Neuroscience, Cognitive Science
Understanding and decoding brain activity into visual representations is a fundamental challenge at the intersection of neuroscience and artificial intelligence. While electroencephalogram (EEG) visual decoding has shown promise due to its non-invasive and low-cost nature, existing methods suffer from Hierarchical Neural Encoding Neglect (HNEN), a critical limitation in which flat neural representations fail to model the brain’s hierarchical visual processing. Inspired by the hierarchical organization of visual cortex, we propose ViEEG, a neuro-inspired framework that addresses HNEN. ViEEG decomposes each visual stimulus into three biologically aligned components, namely contour, foreground object, and contextual scene, which serve as anchors for a three-stream EEG encoder. These EEG features are progressively integrated via cross-attention routing, simulating cortical information flow from low-level to high-level vision. We further adopt hierarchical contrastive learning for EEG-CLIP representation alignment, enabling zero-shot object recognition. Extensive experiments on THINGS-EEG dataset demonstrate that ViEEG significantly outperforms previous methods by a large margin in both subject-dependent and subject-independent settings. Results on THINGS-MEG dataset further confirm ViEEG's generalization to different neural modalities. Our framework not only advances the performance frontier but also sets a new paradigm for EEG brain decoding. Code and pretrained models will be available.