Large language models (LLMs) have demonstrated strong performance in various robot control tasks. However, their deployment in real-world applications remains constrained. Even state-ofthe-art LLMs, such as GPT-o4mini, frequently produce invalid action plans that violate physical constraints, such as directing a robot to an unreachable location or causing collisions between robots. This issue primarily arises from a lack of awareness of these physical constraints during the reasoning process. To address this issue, we propose a novel framework that integrates reinforcement learning with verifiable rewards (RLVR) to incentivize knowledge of physical constraints into LLMs to induce constraints-aware reasoning during plan generation. In this approach, only valid action plans that successfully complete a control task receive positive rewards. We applied our method to two small-scale LLMs: a non-reasoning Qwen2.5-3B-Instruct and a reasoning Qwen3-4B. The experiment results demonstrate that constraint-aware small LLMs largely outperform large-scale models without constraints, grounded on both the BoxNet task and a newly developed BoxNet3D environment built using MuJoCo. This work highlights the effectiveness of grounding even small LLMs with physical constraints to enable scalable and efficient multi-robot control in complex, physically constrained environments.
The average treatment effect (ATE) is widely used to evaluate the effectiveness of drugs and other medical interventions. In safety-critical applications like medicine, reliable inferences about the ATE typically require valid uncertainty quantification, such as through confidence intervals (CIs). However, estimating treatment effects in these settings often involves sensitive data that must be kept private. In this work, we present PrivATE, a novel machine learning framework for computing CIs for the ATE under differential privacy. Specifically, we focus on deriving valid privacy-preserving CIs for the ATE from observational data. Our PrivATE framework consists of three steps: (i) estimating a differentially private ATE through output perturbation; (ii) estimating the differentially private variance through a truncated output perturbation mechanism; and (iii) constructing the CIs while accounting for the uncertainty from both the estimation and privatization steps. Our PrivATE framework is model agnostic, doubly robust, and ensures valid CIs. We demonstrate the effectiveness of our framework using synthetic and real-world medical datasets. To the best of our knowledge, we are the first to derive a general, doubly robust framework for valid CIs of the ATE under ($\varepsilon$, $\delta$)-differential privacy.
This article investigates the robustness of rate-splitting multiple access (RSMA) in multi-user multiple-input multiple-output (MIMO) systems to interference attacks against channel acquisition induced by beyond-diagonal RISs (BD-RISs). Two primary attack strategies, random and aligned interference, are proposed for fully connected and group-connected BD-RIS architectures. Valid random reflection coefficients are generated exploiting the Takagi factorization, while potent aligned interference attacks are achieved through optimization strategies based on a quadratically constrained quadratic program (QCQP) reformulation followed by projections onto the unitary manifold. Our numerical findings reveal that, when perfect channel state information (CSI) is available, RSMA behaves similarly to space-division multiple access (SDMA) and thus is highly susceptible to the attack, with BD-RIS inducing severe performance loss and significantly outperforming diagonal RIS. However, under imperfect CSI, RSMA consistently demonstrates significantly greater robustness than SDMA, particularly as the system's transmit power increases.
Conformal prediction (CP) is a popular frequentist framework for representing uncertainty by providing prediction sets that guarantee coverage of the true label with a user-adjustable probability. In most applications, CP operates on confidence scores coming from a standard (first-order) probabilistic predictor (e.g., softmax outputs). Second-order predictors, such as credal set predictors or Bayesian models, are also widely used for uncertainty quantification and are known for their ability to represent both aleatoric and epistemic uncertainty. Despite their popularity, there is still an open question on ``how they can be incorporated into CP''. In this paper, we discuss the desiderata for CP when valid second-order predictions are available. We then introduce Bernoulli prediction sets (BPS), which produce the smallest prediction sets that ensure conditional coverage in this setting. When given first-order predictions, BPS reduces to the well-known adaptive prediction sets (APS). Furthermore, when the validity assumption on the second-order predictions is compromised, we apply conformal risk control to obtain a marginal coverage guarantee while still accounting for epistemic uncertainty.
Effective condition monitoring in complex systems requires identifying change points (CPs) in the frequency domain, as the structural changes often arise across multiple frequencies. This paper extends recent advancements in statistically significant CP detection, based on Selective Inference (SI), to the frequency domain. The proposed SI method quantifies the statistical significance of detected CPs in the frequency domain using $p$-values, ensuring that the detected changes reflect genuine structural shifts in the target system. We address two major technical challenges to achieve this. First, we extend the existing SI framework to the frequency domain by appropriately utilizing the properties of discrete Fourier transform (DFT). Second, we develop an SI method that provides valid $p$-values for CPs where changes occur across multiple frequencies. Experimental results demonstrate that the proposed method reliably identifies genuine CPs with strong statistical guarantees, enabling more accurate root-cause analysis in the frequency domain of complex systems.
Actor-Critic methods are widely used for their scalability, yet existing theoretical guarantees for infinite-horizon average-reward Markov Decision Processes (MDPs) often rely on restrictive ergodicity assumptions. We propose NAC-B, a Natural Actor-Critic with Batching, that achieves order-optimal regret of $\tilde{O}(\sqrt{T})$ in infinite-horizon average-reward MDPs under the unichain assumption, which permits both transient states and periodicity. This assumption is among the weakest under which the classic policy gradient theorem remains valid for average-reward settings. NAC-B employs function approximation for both the actor and the critic, enabling scalability to problems with large state and action spaces. The use of batching in our algorithm helps mitigate potential periodicity in the MDP and reduces stochasticity in gradient estimates, and our analysis formalizes these benefits through the introduction of the constants $C_{\text{hit}}$ and $C_{\text{tar}}$, which characterize the rate at which empirical averages over Markovian samples converge to the stationary distribution.
De novo 3D molecule generation is a pivotal task in drug discovery. However, many recent geometric generative models struggle to produce high-quality 3D structures, even if they maintain 2D validity and topological stability. To tackle this issue and enhance the learning of effective molecular generation dynamics, we present Megalodon-a family of scalable transformer models. These models are enhanced with basic equivariant layers and trained using a joint continuous and discrete denoising co-design objective. We assess Megalodon's performance on established molecule generation benchmarks and introduce new 3D structure benchmarks that evaluate a model's capability to generate realistic molecular structures, particularly focusing on energetics. We show that Megalodon achieves state-of-the-art results in 3D molecule generation, conditional structure generation, and structure energy benchmarks using diffusion and flow matching. Furthermore, doubling the number of parameters in Megalodon to 40M significantly enhances its performance, generating up to 49x more valid large molecules and achieving energy levels that are 2-10x lower than those of the best prior generative models.
Although diversity in NLP datasets has received growing attention, the question of how to measure it remains largely underexplored. This opinion paper examines the conceptual and methodological challenges of measuring data diversity and argues that interdisciplinary perspectives are essential for developing more fine-grained and valid measures.
Large language models (LLMs) have the potential to revolutionize smart home assistants by enhancing their ability to accurately understand user needs and respond appropriately, which is extremely beneficial for building a smarter home environment. While recent studies have explored integrating LLMs into smart home systems, they primarily focus on handling straightforward, valid single-device operation instructions. However, real-world scenarios are far more complex and often involve users issuing invalid instructions or controlling multiple devices simultaneously. These have two main challenges: LLMs must accurately identify and rectify errors in user instructions and execute multiple user instructions perfectly. To address these challenges and advance the development of LLM-based smart home assistants, we introduce HomeBench, the first smart home dataset with valid and invalid instructions across single and multiple devices in this paper. We have experimental results on 13 distinct LLMs; e.g., GPT-4o achieves only a 0.0% success rate in the scenario of invalid multi-device instructions, revealing that the existing state-of-the-art LLMs still cannot perform well in this situation even with the help of in-context learning, retrieval-augmented generation, and fine-tuning. Our code and dataset are publicly available at https://github.com/BITHLP/HomeBench.
Recent large reasoning models such as DeepSeek-R1 exhibit strong complex problems solving abilities by generating long chain-of-thought (CoT) reasoning steps. It is challenging to directly train small language models (SLMs) to emerge long CoT. Thus, distillation becomes a practical method to enable SLMs for such reasoning ability. However, the long CoT often contains a lot of redundant contents (e.g., overthinking steps) which may make SLMs hard to learn considering their relatively poor capacity and generalization. To address this issue, we propose a simple-yet-effective method to prune unnecessary steps in long CoT, and then employ an on-policy method for the SLM itself to curate valid and useful long CoT training data. In this way, SLMs can effectively learn efficient long CoT reasoning and preserve competitive performance at the same time. Experimental results across a series of mathematical reasoning benchmarks demonstrate the effectiveness of the proposed method in distilling long CoT reasoning ability into SLMs which maintains the competitive performance but significantly reduces generating redundant reasoning steps.
Computational dance generation is crucial in many areas, such as art, human-computer interaction, virtual reality, and digital entertainment, particularly for generating coherent and expressive long dance sequences. Diffusion-based music-to-dance generation has made significant progress, yet existing methods still struggle to produce physically plausible motions. To address this, we propose Plausibility-Aware Motion Diffusion (PAMD), a framework for generating dances that are both musically aligned and physically realistic. The core of PAMD lies in the Plausible Motion Constraint (PMC), which leverages Neural Distance Fields (NDFs) to model the actual pose manifold and guide generated motions toward a physically valid pose manifold. To provide more effective guidance during generation, we incorporate Prior Motion Guidance (PMG), which uses standing poses as auxiliary conditions alongside music features. To further enhance realism for complex movements, we introduce the Motion Refinement with Foot-ground Contact (MRFC) module, which addresses foot-skating artifacts by bridging the gap between the optimization objective in linear joint position space and the data representation in nonlinear rotation space. Extensive experiments show that PAMD significantly improves musical alignment and enhances the physical plausibility of generated motions. This project page is available at: https://mucunzhuzhu.github.io/PAMD-page/.
This paper presents a comprehensive review of the 1st Challenge on Video Quality Enhancement for Video Conferencing held at the NTIRE workshop at CVPR 2025, and highlights the problem statement, datasets, proposed solutions, and results. The aim of this challenge was to design a Video Quality Enhancement (VQE) model to enhance video quality in video conferencing scenarios by (a) improving lighting, (b) enhancing colors, (c) reducing noise, and (d) enhancing sharpness - giving a professional studio-like effect. Participants were given a differentiable Video Quality Assessment (VQA) model, training, and test videos. A total of 91 participants registered for the challenge. We received 10 valid submissions that were evaluated in a crowdsourced framework.
Spatial hearing, the brain's ability to use auditory cues to identify the origin of sounds, is crucial for everyday listening. While simplified paradigms have advanced the understanding of spatial hearing, their lack of ecological validity limits their applicability to real-life conditions. This study aims to address this gap by investigating the effects of listener movement, reverberation, and distance on localisation accuracy in a more ecologically valid context. Participants performed active localisation tasks with no specific instructions on listening strategy, in either anechoic or reverberant conditions. The results indicate that the head movements were more frequent in reverberant environments, suggesting an adaptive strategy to mitigate uncertainty in binaural cues due to reverberation. While distance did not affect the listening strategy, it influenced the localisation performance. Our outcomes suggest that listening behaviour is adapted depending on the current acoustic conditions to support an effective perception of the space.
While Large Language Models (LLMs) can generate fluent and convincing responses, they are not necessarily correct. This is especially apparent in the popular decompose-then-verify factuality evaluation pipeline, where LLMs evaluate generations by decomposing the generations into individual, valid claims. Factuality evaluation is especially important for medical answers, since incorrect medical information could seriously harm the patient. However, existing factuality systems are a poor match for the medical domain, as they are typically only evaluated on objective, entity-centric, formulaic texts such as biographies and historical topics. This differs from condition-dependent, conversational, hypothetical, sentence-structure diverse, and subjective medical answers, which makes decomposition into valid facts challenging. We propose MedScore, a new approach to decomposing medical answers into condition-aware valid facts. Our method extracts up to three times more valid facts than existing methods, reducing hallucination and vague references, and retaining condition-dependency in facts. The resulting factuality score significantly varies by decomposition method, verification corpus, and used backbone LLM, highlighting the importance of customizing each step for reliable factuality evaluation.
An objective, face-valid way to assess the originality of creative ideas is to measure how rare each idea is within a population -- an approach long used in creativity research but difficult to automate at scale. Tabulating response frequencies via manual bucketing of idea rephrasings is labor-intensive, error-prone, and brittle under large corpora. We introduce a fully automated, psychometrically validated pipeline for frequency-based originality scoring. Our method, MuseRAG, combines large language models (LLMs) with an externally orchestrated retrieval-augmented generation (RAG) framework. Given a new idea, the system retrieves semantically similar prior idea buckets and zero-shot prompts the LLM to judge whether the new idea belongs to an existing bucket or forms a new one. The resulting buckets enable computation of frequency-based originality metrics. Across five datasets (N=1143, n_ideas=16294), MuseRAG matches human annotators in idea clustering structure and resolution (AMI = 0.59) and in participant-level scoring (r = 0.89) -- while exhibiting strong convergent and external validity. Our work enables intent-sensitive, human-aligned originality scoring at scale to aid creativity research.
Graph Neural Networks (GNNs) have gained prominence for their ability to process graph-structured data across various domains. However, interpreting GNN decisions remains a significant challenge, leading to the adoption of saliency maps for identifying influential nodes and edges. Despite their utility, the reliability of GNN saliency maps has been questioned, particularly in terms of their robustness to noise. In this study, we propose a statistical testing framework to rigorously evaluate the significance of saliency maps. Our main contribution lies in addressing the inflation of the Type I error rate caused by double-dipping of data, leveraging the framework of Selective Inference. Our method provides statistically valid $p$-values while controlling the Type I error rate, ensuring that identified salient subgraphs contain meaningful information rather than random artifacts. To demonstrate the effectiveness of our method, we conduct experiments on both synthetic and real-world datasets, showing its effectiveness in assessing the reliability of GNN interpretations.
Developing new molecular compounds is crucial to address pressing challenges, from health to environmental sustainability. However, exploring the molecular space to discover new molecules is difficult due to the vastness of the space. Here we introduce CoCoGraph, a collaborative and constrained graph diffusion model capable of generating molecules that are guaranteed to be chemically valid. Thanks to the constraints built into the model and to the collaborative mechanism, CoCoGraph outperforms state-of-the-art approaches on standard benchmarks while requiring up to an order of magnitude fewer parameters. Analysis of 36 chemical properties also demonstrates that CoCoGraph generates molecules with distributions more closely matching real molecules than current models. Leveraging the model's efficiency, we created a database of 8.2M million synthetically generated molecules and conducted a Turing-like test with organic chemistry experts to further assess the plausibility of the generated molecules, and potential biases and limitations of CoCoGraph.
Large Language Models (LLMs) are increasingly evaluated on multiple-choice question answering (MCQA) tasks using *first-token probability* (FTP), which selects the answer option whose initial token has the highest likelihood. While efficient, FTP can be fragile: models may assign high probability to unrelated tokens (*misalignment*) or use a valid token merely as part of a generic preamble rather than as a clear answer choice (*misinterpretation*), undermining the reliability of symbolic evaluation. We propose a simple solution: the *prefilling attack*, a structured natural-language prefix (e.g., "*The correct option is:*") prepended to the model output. Originally explored in AI safety, we repurpose prefilling to steer the model to respond with a clean, valid option, without modifying its parameters. Empirically, the FTP with prefilling strategy substantially improves accuracy, calibration, and output consistency across a broad set of LLMs and MCQA benchmarks. It outperforms standard FTP and often matches the performance of open-ended generation approaches that require full decoding and external classifiers, while being significantly more efficient. Our findings suggest that prefilling is a simple, robust, and low-cost method to enhance the reliability of FTP-based evaluation in multiple-choice settings.
Deep learning-based models have demonstrated remarkable success in solving illposed inverse problems; however, many fail to strictly adhere to the physical constraints imposed by the measurement process. In this work, we introduce a projection-based correction method to enhance the inference of deep inverse networks by ensuring consistency with the forward model. Specifically, given an initial estimate from a learned reconstruction network, we apply a projection step that constrains the solution to lie within the valid solution space of the inverse problem. We theoretically demonstrate that if the recovery model is a well-trained deep inverse network, the solution can be decomposed into range-space and null-space components, where the projection-based correction reduces to an identity transformation. Extensive simulations and experiments validate the proposed method, demonstrating improved reconstruction accuracy across diverse inverse problems and deep network architectures.
Although Generative Flow Networks (GFlowNets) are designed to capture multiple modes of a reward function, they often suffer from mode collapse in practice, getting trapped in early discovered modes and requiring prolonged training to find diverse solutions. Existing exploration techniques may rely on heuristic novelty signals. We propose Loss-Guided GFlowNets (LGGFN), a novel approach where an auxiliary GFlowNet's exploration is directly driven by the main GFlowNet's training loss. By prioritizing trajectories where the main model exhibits high loss, LGGFN focuses sampling on poorly understood regions of the state space. This targeted exploration significantly accelerates the discovery of diverse, high-reward samples. Empirically, across various benchmarks including grid environments, structured sequence generation, and Bayesian structure learning, LGGFN consistently enhances exploration efficiency and sample diversity compared to baselines. For instance, on a challenging sequence generation task, it discovered over 40 times more unique valid modes while simultaneously reducing the exploration error metric by approximately 99\%.