Artificial Intelligence
Size Generalization for Diffusion Routing Solvers
Barak Itzchak Davidovitch, Eli Meirom, Ethan Fetaya et al. (+1 more)
Routing problems, like the Traveling Salesman Problem (TSP) and the Capacitated Vehicle Routing Problem (CVRP), are NP-hard and slow to solve for large instances.
Diffusion-based solvers can be trained in a supervised way using sets of optimal solutions, and then quickly solve new test instances. However, for large instances, optimal solutions are hard to find, and
diffusion models fail to generalize to instance sizes outside their training distribution. Here we describe ResizeCO, a label free size-generalization approach that addresses both the change in statistical properties of larger instances, and the computational challenge of solving them quickly. It uses reinforcement learning on large-scale instances to adapt a
diffusion model trained on small instances. Specifically, we adapt GRPO to this problem, using route length as the training signal. ResizeCO also formulates k-opt as a tree search, solved by a beam search on the GPU. In size-generalization experiments on TSP and CVRP instances with up to 10000 nodes, ResizeCO achieves a Pareto front over route quality and time that dominates learned solvers, and also outperforms other solvers at short run times, setting a new state of the art.
Read the full abstract ▾
All authors Barak Itzchak Davidovitch, Eli Meirom, Ethan Fetaya, Gal Chechik
Machine Learning
FreeSolo: Linear-time Sparse Attention with Zero-Shot Length Extrapolation
Zekun Shi and Alastair James Arthur Price
Linear-time sequence models typically store long-context information in a recurrent state. A fixed-size state limits how much information can be stored, while hybrid architectures that add full
attention for better recall incur quadratic sequence cost. Alternatively, sparse
attention with continued pretraining (CPT) can extend the effective context length. Generalization beyond the trained length remains challenging, however, and CPT can be costly. We introduce FreeSolo, a native sparse
attention mechanism with a short-range sliding window branch and a long-range branch that selects keypoint
cells for direct
token attention. Its linear-time variant, FS-L, learns to prune the prefix before query-dependent selection through short CPT. FS-B searches balanced trees with $O(N\log^2 N)$ algorithmic cost including radix-sort construction. FreeSolo demonstrates better zero-shot length extrapolation than the baselines without long-context fine-tuning.
Read the full abstract ▾
Machine Learning
CartoVec: General-Purpose Location Embeddings from Open Map Data
Furkan Gursoy
Geographic coordinates are common inputs in applied machine learning, but latitude and longitude describe position rather than the surrounding environment. Image-grounded location encoders learn this context from satellite or ground-level imagery; structured open map data offers another source of supervision whose utility for continuous coordinate encoders remains less explored. We introduce CartoVec, a coordinate encoder trained to predict Overture-derived land cover, land use, transportation, place and connectivity targets at multiple spatial scales, without image inputs or downstream-task labels. We evaluate frozen
embeddings on Census outcomes, Airbnb prices and Philadelphia crime in the US Northeast using spatial block cross-validation. CartoVec has the highest mean performance on most Census outcomes and the highest average across the full suite, with several comparisons close across folds. The findings support open map data as a practical source of reusable location representations with a coordinate-to-vector interface that requires no map lookup at inference. The open-weight model is available at https://huggingface.co/gursoyfurkan/CartoVec.
Read the full abstract ▾
Computation and Language
Soft Teacher Forcing
Mohammad Fahes, Cordelia Schmid and Anurag Arnab
Soft
tokens have so far been used to replace discrete chain-of-thought in latent
reasoning methods. These approaches typically require multi-stage training and, in some cases, auxiliary modules, yet they still underperform supervised fine-tuning (SFT) on <input, chain-of-thought, output> triples. In this paper, we ask whether soft
tokens can be used to improve SFT itself, instead of as an avenue for latent
reasoning. We introduce Soft Teacher Forcing (Soft-TF), a simple training
algorithm that combines teacher-forced
embeddings with soft
tokens through random convex combinations. The soft
tokens are computed in a single parallel forward pass over the ground-truth sequence. Soft-TF adds no parameters, no external model and no curriculum, and leaves inference unchanged. Experiments show that Soft-TF improves over SFT on GSM8K, MATH, MathQA and AQuA, by +2.1 to +4.1 points on GSM8K across seven Gemma, Llama and Mistral models.
Read the full abstract ▾
Sound · Cross-listed from eess.AS
MSVAE: Rethinking Musical Semantics in Continuous Latent Spaces
Guobin Ma, Yuepeng Jiang, Dake Guo et al. (+15 more)
Continuous latent representations underlie recent
diffusion-based lyrics-to-song and text-to-music systems, yet aligning lyric conditions with these latents remains difficult: existing systems resort to generator-side machinery such as sentence-level timestamps, auxiliary
alignment objectives, or semi-autoregressive decoding, while the latents they predict are still produced by autoencoders trained purely for reconstruction. We address this difficulty from the representation side. We propose MSVAE (Music Semantic Variational Autoencoder), which structures its continuous latent around two complementary semantic streams: work-level compositional content and lyric-level linguistic-vocal content. Partitioned dual-stream
alignment makes both streams explicit by aligning disjoint latent subspaces with frozen lead-sheet and ASR references, while a semantic-first gated residual posterior derives its base from a frozen music-SSL encoder and admits acoustic information only through gated, bounded corrections. MSVAE achieves competitive stereo reconstruction and stronger MARBLE probing than continuous-autoencoder baselines, and improves downstream lyrics-to-song and text-to-music generation. Notably, with only an untimed phoneme prefix and no lyric timing, MSVAE yields the lowest phoneme error rate, whereas all baseline representations require sentence-level
alignment to produce intelligible vocals.
Read the full abstract ▾
All authors Guobin Ma, Yuepeng Jiang, Dake Guo, Huakang Chen, Yuan Zhou, Lingxin Xiong, Wenkai Cheng, Jingbin Hu, Hanke Xie, Chunbo Hao, Wenhao Li, Ziqian Ning, Jixun Yao, Jian Zhao, Zhonglin Jiang, Yong Chen, Lei Xie, Pengcheng Zhu
Computation and Language
DuoDiscover: Scaling Autonomous Discovery Beyond the Evaluation Bottleneck
Shubham Agarwal, Akshat Gupta, Mike Heddes et al. (+21 more)
Evaluation has been central to advances in AI, and it is equally critical to autonomous discovery. Yet scaling autonomous discovery to real-world engineering challenges faces a fundamental bottleneck: the cost of evaluating progress. In real settings, a single true evaluation, such as a full
benchmark or serving trace, can take hours, so a search can afford only a handful of true evaluations. We present DuoDiscover, a search system that jointly discovers what to optimize and how to evaluate progress efficiently, through three mechanisms. First, each worker in a fleet of coding
agents co-discovers an optimization target and a fast, tailored proxy evaluator, which we call a yardstick. The
agent then hill-climbs the yardstick rather than the true evaluation. Second, since search can exploit gaps between a yardstick and the true objective, fidelity tests continually recheck each yardstick's ranking and invalidate any that drift. Third, the fleet is bottom-up, with no central decomposition of the problem. A lightweight orchestrator spawns and terminates
agents, briefs running ones, and seeds new
agents with others' confirmed work. DuoDiscover enables autonomous optimization from software to chip architecture. We demonstrate DuoDiscover on two repository-level
benchmarks and four GPU and TPU kernel suites covering hundreds of kernels. On SWE-fficiency, it doubles the average speedup of human experts. On SOL-Exec, it ranks first on 121 of 235 kernels and in the top three on 212. On the heavily optimized vLLM and SQLite engines, DuoDiscover achieves 1.92$\times$ and 1.38$\times$ gains over the base code. On a CPU microarchitecture optimization task with evaluations of up to 28 hours, DuoDiscover surpasses both AlphaEvolve-based ArchAgent v2 and the best human design, with 1.65$\times$ ArchAgent v2's gain in 16.7 days versus more than 40 days, advancing the frontier of autonomous chip design.
Read the full abstract ▾
All authors Shubham Agarwal, Akshat Gupta, Mike Heddes, Dilara Soylu, Rui Meng, Patrick Tser Jern Kon, Jiefeng Chen, Mert Cemri, Shu Liu, Abe Gonzalez, Akanksha Jain, Bhavana Dalvi Mishra, Linfeng Song, Vilobh Meshram, Xiangru Tang, Jinsung Yoon, Aditya Parameswaran, Ion Stoica, Vahab Mirrokni, Burak Gokturk, Parthasarathy Ranganathan, Tomas Pfister, Nanyun Peng, Chun-Liang Li
Artificial Intelligence
Aotian Chen, Frazier N. Baker, Reza Averly et al. (+5 more)
Current chemistry
benchmarks primarily evaluate outcome prediction or reaction pathway generation, but rarely test whether a model can explain why an observed chemical effect occurs. We introduce ChemExplain, a
benchmark of 1,180 multiple-choice chemistry questions drawn from 383 peer-reviewed papers. Each question pairs a molecular or reaction image with an observed chemical effect and four candidate explanations, each associated with a different structural feature visible in the image. Answering requires the model to perceive the depicted structure, apply chemical knowledge, and identify which feature most directly explains the effect, a capability we term explanatory attribution. The correct feature-mechanism relation is derived from supporting evidence in the source paper rather than invented by the question-generation LLM. We construct the
benchmark automatically with a multi-
agent framework that applies progressive quality control at three stages and validate it with eight chemistry domain experts. The strongest evaluated model reaches 78.6% accuracy, leaving considerable room for improvement. On a 600-question expert-reviewed subset,
reasoning-trace analysis classifies 71.4% of the strongest model's errors as attribution failures. Attribution is also the largest error category for the open-source and chemistry-specific models included in our analysis.
Read the full abstract ▾
All authors Aotian Chen, Frazier N. Baker, Reza Averly, Shan Zhang, Tianao Chen, Daniel Adu-Ampratwum, Xia Ning, Yuan Xue
Machine Learning
ModRes: A modification of the ResPlan dataset ready for floor plan analysis and graph machine learning
Emma Shelley, Wassim Jabi, Thomas Woolley et al. (+1 more)
Floor plan
datasets underpin computational analysis of building layouts, spatial connectivity and graph machine learning. However, publicly available
datasets often require substantial preprocessing before they can be used reliably. We present ModRes, a cleaned and enriched version of the ResPlan
dataset, containing 8,431 valid and unique residential floor plans. Invalid and duplicate floor plans are removed through a dedicated cleaning workflow, producing a ready-to-use
dataset. For each floor plan, ModRes provides two-dimensional geometry, images, three-dimensional building representations and three complementary dual graphs in CSV and JSON formats with graph-, node- and edge-level features. Continuous and categorical graph attributes support machine learning workflows. We characterise the
dataset using graph-based statistics and demonstrate its utility through a range of case studies. ModRes provides structured
geometric, topological and semantic representations needed to automate spatial analysis and support machine learning-based workflows for building design and performance evaluation.
Read the full abstract ▾
All authors Emma Shelley, Wassim Jabi, Thomas Woolley, Katerina Kaouri
Machine Learning
FunDM: Cheap & Label-Free Decision Models from Frozen Language Models
Ujjawal K. Panchal
Decision models such as Jev score candidate answers or actions. A small decision head trained label-free can recover about 99% of a frozen
language model's multiple-choice accuracy while using only two-thirds of its
transformer layers. It learns the full model's answer probabilities with KL divergence, without correct-answer labels for training. One backbone pass reads the question and all options together; the head returns probabilities for every option. We call this model FunDM (Fun Decision Model). Using 24 of Qwen3-8B's 36 layers and skipping the LM head, its +1T variant reaches 75.0% mean accuracy over eight
benchmarks, versus 75.7% for the full model. On MMLU-Pro, both heads achieve 1.56 to 1.57 times batched vLLM throughput with about one-third lower peak GPU allocator
memory. Both heads score higher than released Contrastive
Language Models (CLM), fine-tuned CLM, and CLM-shaped heads trained from scratch on the eight multiple-choice
benchmarks and coding-
agent selection. Separately trained
agent heads learn judge probabilities without pass/fail labels and select passing runs for 74.4 to 74.6 of 100 held-out tasks on average, versus 74 for the full-model judge and 52.0 for a CLM-shaped action-trained head. Code is available at: https://github.com/Ujjawal-K-Panchal/FunDM
Read the full abstract ▾
Robotics
Generative Flow on Symbolic Abstractions for Embodiment Capability Discovery
Youwei Yu and Lantao Liu
Achieving complex, long-horizon
robot behavior remains challenging because successful execution depends on skills grounded in a
robot's physical affordances. Existing training-task distributions are often handcrafted or sampled from large
language models (LLMs), relying on semantic plausibility rather than embodiment-specific feasibility. This mismatch can produce curricula that are too difficult, redundant, or blind to non-obvious but learnable behaviors. We propose Generative Flow on Symbolic Abstractions (FOSA), a framework for discovering embodiment-specific capabilities by learning a grounded task generator. FOSA parameterizes an abstract policy as a Generative Flow Network that constructs symbolic task skeletons. Each skeleton is compiled into a simulation environment, where low-level policy-learning performance provides the reward signal for the abstract policy. Across heterogeneous
robot platforms, FOSA discovers diverse and executable tasks near the
robot's empirical capability frontier. After distilling the discovered task policies into a single
language-conditioned policy, FOSA improves performance on unseen complex and long-horizon tasks. The code and demonstration
videos are available at https://www.youwei-yu.com/fosa.
Read the full abstract ▾
Data Structures and Algorithms
A Better-than-$2$ Approximation for $k$-Median Part II: Stable Instances
Rares-Darius Buhai, Vincent Cohen-Addad, Henry Fleischmann et al. (+6 more)
We consider the $k$-median problem on general metric spaces, subject to the condition that the instances are $\beta$-stable (i.e., the optimal solution using $k-1$ centers has a cost at least $(1+\beta)$ times that of the optimal solution with $k$ centers). We give a $(1.89+\epsilon)$-approximation
algorithm for such instances running in time $\exp(1/(\beta \times \mathrm{poly}(\epsilon)))\cdot \mathrm{poly}_{\epsilon}(n)$. In particular, for $\beta =\mathrm{poly}(\epsilon)/\log n$ and $\epsilon$ a tiny constant, this is a
polynomial-time
algorithm. This improves on previous work showing a $(2 + \epsilon)$-approximation
algorithm with similar running time [CGL+25]. Combined with the pseudo-approximation
algorithm in our companion work, this results in a better-than-$2$ approximation
algorithm for general $k$-median instances. Our main technical contribution is a novel nuanced analysis of local search that allows us to isolate a subset of clients on which we lose essentially nothing compared to the optimal solution, while losing an approximation factor of $3$ on the rest of the clients. We complement this with an
algorithm based on sampling and partial enumeration, achieving a better-than-$2$ approximation on the rest of the clients. Trading off these two
algorithms yields our final approximation.
Read the full abstract ▾
All authors Rares-Darius Buhai, Vincent Cohen-Addad, Henry Fleischmann, Anupam Gupta, Antoni Jubés Monforte, Madhusudhan Reddy Pittu, Miltiadis Stouras, Ola Svensson, Lukas Vogl
Machine Learning · Cross-listed from cond-mat.mtrl-sci
Comprehensive Workflow for Uncertainty-Aware Ionic Liquid Solvent Discovery
Alexander Lobo, Urvi Awasthi and Leonid Zhukov
Designing synthesizable materials with targeted properties remains one of the central objectives in materials sciences. Ionic
liquids (ILs) are well suited to this goal due to their "tunability", where physical and chemical properties can be precisely customized by modifying their molecular structure, specifically by varying the combination of cations and anions. At the same time, current data-driven property models for ionic
liquids often degrade in scarce, noisy, and uneven data regimes, where measurements cover only a small fraction of chemical space and a limited range of thermodynamic conditions. This makes out-of-distribution screening brittle: even when point predictions look plausible, it is difficult to compare candidates consistently, quantify downstream implications, or trust rankings enough to guide molecular discovery. We present a property-prediction and optimal candidate selection workflow that treats data processing, deep learning modeling, and physics-based calculations as a coupled system, linking property prediction with uncertainty estimation and physics-based filtering. By tightening the link between predicted properties and the criteria used for down-selection, the workflow supports reliable out-of-distribution ranking and enables prioritization of previously untested ionic
liquid candidates with favorable predicted trade-offs. We demonstrate the application of our workflow by designing novel ionic
liquids for CO2 capture from flue gas, predicting their properties and selecting Pareto-optimal candidates based on CO2 solubility, IL viscosity and working capacity.
Read the full abstract ▾
Emerging Technologies
PRIM: Energy- and Endurance-Aware Compiler Optimization for Digital Compute in Non-volatile Memory
Patrick Miller and Ulya R. Karpuzcu
Compute-in-
Memory (CiM) is an alternative computing paradigm that circumvents the
memory bandwidth bottleneck. Variants utilizing non-volatile
memory cells (NVCiM) to perform Boolean operations directly within
memory arrays offer significant density and energy-efficiency advantages. Fully realizing this potential, however, requires NVCiM-specific compiler optimizations. In conventional digital NVCiM systems, an output
cell must be written – or preset – to an operation-specific value before any Boolean operation can occur. Preset-induced extra writes can degrade energy efficiency and
cell endurance, often to the point of negating CiM's efficiency gains. In this paper, we introduce PRIM (Preset Reduction In
Memory), a compiler optimization framework tailored for digital NVCiM that effectively minimizes preset overhead without compromising computational accuracy or architectural complexity. Unlike existing optimization approaches, PRIM is not restricted to specific types of Boolean operations. Experimental results show that PRIM can reduce execution time and energy consumption by up to 50/% and 44/%, respectively, while boosting
cell endurance by up to 50/%.
Read the full abstract ▾
Artificial Intelligence
Learning Perceptual Geometry of Natural Odor Mixtures from LLM-Derived Descriptors
Farhad Pashakhanloo and Venkatesh N. Murthy
The relationship between odor chemistry and perception remains incompletely understood. Many existing studies focus on the perception of single molecules, whereas natural odors contain tens to hundreds of components, adding extra layer of complexity to percept formation. Here, we explore the relationship between molecular composition and perceived similarity in natural odor objects. We study this using a database of more than 1,200 volatile-compound-in-food mixtures containing more than 8,000 molecular components, and use large
language models (LLMs) as a scalable surrogate for deriving mixture-level perceptual descriptions. We find that
language-derived representations provide useful supervision for predicting held-out mixture similarities from molecular composition. The prediction was consistently strongest when perceptual targets were derived from chemosensory
prompts than from other sensory
prompts. Further, during the mixture-level training, we learned low-rank molecular
embeddings that enabled better prediction of held-out mixture similarities than component-overlap metrics, even for mixture pairs with no shared molecules. Although no single-molecule labels were used during training, the learned molecular geometry showed significant
alignment with the independent human odor-descriptor space. Finally, we explored the use of external molecular features in our mixture-similarity prediction task. These features showed modest zero-shot
alignment with mixture-level perceptual similarity. They improved prediction under limited supervision but offered little additional predictive benefit with the full training set. Together, these results show that
language-derived descriptions can provide scalable supervision for predicting the perceptual organization of complex natural mixtures, contributing to a quantitative understanding of how molecular composition gives rise to odor perception.
Read the full abstract ▾
Robotics
Force-Modulated Dexterity: Unified Compliance for Contact-Rich Manipulation
Ying Yuan, David Held, Jitendra Malik et al. (+1 more)
Teleoperation is widely used to collect high-quality demonstrations for
robot learning. Dexterous manipulation, however, requires coordinated control of motion and contact forces. Operators can specify motion, but struggle to reproduce the subtle force adjustments of human manipulation without feeling the
robot's contacts. We introduce Force-Modulated Dexterity (FOMO-Dex), a unified compliance formulation for contact-rich manipulation. FOMO-Dex expresses nominal actions in coordinates defined by task geometry and contact structure. It applies force-driven motion corrections along selected directions while leaving the remaining command components unchanged. Across card picking, paper cutting, screwdriving, and nut-and-bolt assembly, FOMO-Dex reduces excessive contact forces compared with stiff control. A user study shows that operators collect more successful demonstration data per hour after brief practice. For policy learning, imitating the corrected actions improves card-picking success over imitating raw operator commands. Policies trained on FOMO-Dex demonstrations also achieve more rotation in nut-and-bolt manipulation and screwdriving than those trained on demonstrations collected with the stiff controller.
Videos are shown on https://yingyuan0414.github.io/fomo-dex/ .
Read the full abstract ▾
All authors Ying Yuan, David Held, Jitendra Malik, Haozhi Qi
Machine Learning · Cross-listed from stat.ML
A Generalized McDiarmid Inequality: Sample Reuse and Non-Uniform Unbounded Differences
Jeremiah Birrell
We develop a novel generalization of McDiarmid's concentration inequality and use it to obtain a uniform law of large numbers result and error bounds on
stochastic optimization problems which simultaneously incorporate two key features: 1) They capture the benefit of training sample reuse in
algorithms that also employ easily-sampled auxiliary random variables. 2) They allow for one-component mean-difference bounding functions which are both unbounded in the component of interest and have non-uniform dependence on another component. We demonstrate the utility of our method by deriving concentration inequalities for score-based generative modeling. This application naturally leverages both key features of our new tools: 1) It utilizes auxiliary Gaussian random variables in conjunction with the training samples; accounting for training sample reuse results in tighter error bounds by effectively integrating out the dependence on the auxiliary random variables. 2) The ability to handle non-uniform mean-difference bounding functions allows us to treat unbounded score models and data distributions with unbounded support.
Read the full abstract ▾
Artificial Intelligence
The Format is the Filter: Scoring Format Fixes What an LLM Judge Can Express
Lovedeep Gondara, Jekaterina Novikova, Sagarika Suresh et al. (+2 more)
When an LLM judge filters instruction-tuning data, its scoring format (binary verdict, 1–5 rating, 0–100 score, or comparison) is rarely justified or ablated. Holding the candidate pool, judge
prompt, decoding and selection budget fixed, we score 15,406 UltraFeedback candidates under five formats with three judges, curate, fine-tune 66 models, and evaluate them with four judges. A 0–100 scale is worth only 7–12 equally used levels, two to three times a 1–5 scale rather than twenty, and a binary verdict leaves the top score tied in 77–78% of
prompts, so most selections are made at random. These properties are set by the format almost independently of the judge. Kendall's $\tau_b$ hides them: it ranks binary best while $\tau_a$ and top-1 agreement rank it last, because it discounts the ties a selector must break at random. Both comparative formats inherit a slot bias whose sign differs across judges. Downstream, curated data beat random selection under every evaluation judge, robust to length and markdown adjustment, but no ordering among formats is detectable. We propose four quantities that judge-based curation pipelines should report.
Read the full abstract ▾
All authors Lovedeep Gondara, Jekaterina Novikova, Sagarika Suresh, Jack Ji, Jithin Pradeep
Emerging Technologies
Neuromorphic Decoding and Dynamical Image Reconstruction from Populations of Spiking Retinal Ganglion Cells
Ning Zhang and Arto Nurmikko
Decoding visual stimuli from the spiking activity of retinal ganglion
cells (RGCs) informs both our understanding of the retinal code and the design of visual prostheses. Natural
vision is dynamic, yet state-of-the-art decoders mostly reconstruct single frames with artificial neural networks that process dense, continuous-valued signals rather than the retina's sparse, asynchronous spikes. We asked whether dynamic scenes can be reconstructed and tracked entirely within the spike domain, and at what computational cost. We built an end-to-end spiking neural network (SNN) whose
neurons integrate the recorded RGC spikes over time. Populations of up to 1836 RGCs were recorded ex vivo from mouse retina on high-density microelectrode arrays while flashed images, moving bars, drifting gratings and randomly moving handwritten digits were presented. For moving digits, one shared spiking encoder fed two readouts, one reconstructing the image and one decoding the digit's position. Compute energy was estimated from counted synaptic operations. The SNN decoded what and where at once. It reconstructed the stimuli with a structural similarity (SSIM) of up to 0.93, refining the reconstruction as spikes accumulated, and tracked a randomly moving target with a mean error of 1.33 pixels on a $32\times32$ grid. Its fidelity nearly matched that of the best of 17 larger spiking and artificial decoders (5.9 million to 1.7 billion parameters, versus 5.4 million), and at a mean firing rate of 14.2% it needed an estimated $\sim$70-fold less compute energy than a dense artificial network of the same architecture. Dynamic visual scenes can thus be decoded from retinal population activity in the spike domain, with a compact network and at a compute cost compatible with implantable and wearable neural interfaces, supporting spike-native decoders for visual prostheses.
Read the full abstract ▾
Data Structures and Algorithms
Parameterized algorithms for representing graphs as intersections of threshold graphs
L. Sunil Chandran and Suraj Kumar Sahoo
A graph is called a threshold graph if there is an assignment of real valued weights to its vertices such that two vertices have an edge between them if and only if the sum of the weights of the two vertices is above a certain `threshold value'. We will denote the class of all threshold graphs as $TH$. For a graph $G=(V,E)$, if for some integer $t\geq 0$, there are $t$ many threshold graphs $\{G_i=(V,E_i)\}_{i\in [t]}$ such that we have $E=E_1\cap E_2\cap \cdots \cap E_t$, then we say that the collection of threshold graphs $\{G_i=(V,E_i)\}_{i\in [t]}$ forms a $TH$-representation of $G$ of size $t$. \emph{The intersection dimension of $G$ with respect to threshold graphs} (denoted as $dim_{TH}(G)$) is the smallest non-negative integer $t$ such that there is a $TH$-representation of $G$ of size $t$. It is known that for a graph $G$ and integer $t>0$, the problem of deciding whether $dim_{TH}(G)\leq t$ is NP-complete even for $t=3$. In this paper, we study this problem in the framework of parameterized
algorithms. We consider the vertex cover number and the cluster vertex deletion number as our parameters. We give a FPT
algorithm for determining an optimal $TH$-representation of a graph when parameterized by its vertex cover number. Our main result is an efficient parameterized approximation scheme for this problem when parameterized by the cluster vertex deletion number of $G$.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ME
Implicit and explicit reparameterizations of the Folded Normal and Rice distributions
Luis Aldama, Kevin Dalton, Minhuan Li et al. (+1 more)
Variational inference is a flexible tool for modeling experimental data and has proven useful in crystallography. Pathwise gradient
estimators provide low-variance gradients for reparameterized variational inference, but are not readily available for some distributions central to crystallography. This work derives and implements implicit and explicit reparameterized gradient
estimators for the folded Normal and Rice distributions in \prog{PyTorch}, and compares their variance analytically and empirically. In each case the implicit
estimator achieves lower variance for the location derivative, particularly at small location-to-scale ratios, while the scale-derivative variances are nearly equal. For both distributions, implicit
estimator is proved to be the conditional expectation of the explicit
estimator given the sampled magnitude, so its variance is never larger. As a practical application, French-Wilson scaling is formulated as a variational inference problem, using the folded Normal and Rice distributions as variational families for centric and acentric reflections, respectively. Both
estimators recover the exact posterior to better than $1\%$ on the amplitude, and converge at the same rate. The implementations are available in the open-source package \prog{rs-distributions}.
Read the full abstract ▾
All authors Luis Aldama, Kevin Dalton, Minhuan Li, Doeke Hekstra
Sound
ATTEST: Evidence-Grounded Reinforcement Learning for Long-Audio Temporal Understanding
Ashutosh Chaubey, Jinxi Guo, Minh Tran et al. (+2 more)
Temporal grounding is fundamental to audio understanding, yet large audio
language models (LALMs) remain weak at it on long audio, where
hallucinations compound and annotated data is scarce. Existing
benchmarks cover only short clips or offer coarse, synthetic annotations. We introduce EgoSCAPE, a manually verified
benchmark created from Ego4D with 700 real audios of durations up to 5 minutes, annotated with dense captions, sound sources, audio timelines, and temporal grounding queries. We further propose ATTEST, a GRPO-based reinforcement learning framework that improves temporal grounding without changing the base model's architecture or
token vocabulary. ATTEST combines (i) a counterfactual grounding reward penalizing predictions that survive removal of their acoustic evidence, (ii) an
attention-density reward encouraging generation to attend to its own claimed time spans, and (iii)
token-wise advantages giving segment-level credit for long dense captions. ATTEST outperforms prior temporal grounding methods on existing dense captioning and grounding
benchmarks, with fewer
hallucinations. Together, EgoSCAPE and ATTEST establish a rigorous evaluation-training recipe that brings temporally grounded audio understanding closer to practical, long-form deployment.
Read the full abstract ▾
All authors Ashutosh Chaubey, Jinxi Guo, Minh Tran, Michael Andersland, Ozlem Kalinli
Machine Learning · Cross-listed from stat.ML
SCOPE Before You Sample: Conformal Scores Guide Posterior Exploration for Fast and Calibrated Bayesian Predictive Inference
Zahra Moslemi, Ziyi Liang and Babak Shahbaba
Bayesian predictive regions account for parameter uncertainty but can be poorly calibrated under model misspecification, even with expensive full MCMC. Cheaper approximations such as variational inference reduce the cost but often yield less accurate predictive distributions. We propose SCOPE (Score-guided Conformal Posterior Exploration), which retains the predictive quality of full MCMC while achieving calibrated coverage at a fraction of its cost. The key observation is that a prediction region can depend on the posterior mainly through a few parameter directions that move the region's boundary, and these are generally not the directions of largest posterior variance. SCOPE gives nonconformity scores a new role in guiding posterior computation: score gradients on a held-out guide set, weighted toward the target boundary, identify the relevant directions. MCMC explores this subspace, while an inexpensive projected variational approximation carries the remaining uncertainty. The same guide set calibrates the region's final density level. We establish asymptotic coverage for SCOPE and provide a split variant with finite-sample validity. Controlled simulations show that score-guided exploration yields more accurate calibrated regions than non-targeted direction choices at low active rank. Across simulated and real
benchmarks, SCOPE has a median test-NLL gap of only 0.002 nats relative to full
Hamiltonian Monte Carlo (HMC), and on the real
benchmarks it runs 12-15 times faster.
Read the full abstract ▾
Machine Learning
OpenDGO: Benchmarking Multi-Agent Organizations Across Diverse Application Domains
Xunkai Li, Miao Zhang, Zekai Chen et al. (+6 more)
Large
language model (LLM)-based multi-
agent systems are increasingly applied across diverse domains, yet different applications require different forms of
agent organization. Existing studies typically adopt predefined organizations, such as
Star, Chain, and Tree, or learn communication graphs to improve performance on specific tasks. However, these methods are largely designed and evaluated within a limited set of application domains, providing little understanding of whether an organization effective in one domain remains suitable for others with different collaboration requirements. We present OpenDGO, a controlled
benchmark and analysis framework covering six real-world domains and three collaboration settings: Sequential Dependency, Parallel Decomposition, and Information Integration. Under matched tasks,
agents, tools, and resource limits, OpenDGO compares fixed and learned organizations while separately examining communication graphs, role assignments, input assignments, resource budgets, and component failures. Our results show that there is no “one-organization-for-all” solution: preferred organizations vary across applications, and even the same communication graph can yield different outcomes under different role and input assignments. These findings highlight the need for application-dependent organization design, aiming to understand which organization is suitable for a given application, under what conditions, and why.
Read the full abstract ▾
All authors Xunkai Li, Miao Zhang, Zekai Chen, Xuaner Chen, Yu liu, Rui Qian, Xun Wu, Hongchao Qin, Rong-Hua Li
Numerical Analysis
Analytical and numerical periodic homogenization of Hamilton–Jacobi–Bellman and Isaacs equations in a $W^{2,p}$ Cordes framework
Timo Sprekeler and Hung V. Tran
We study periodic homogenization of fully-nonlinear second-order Hamilton–Jacobi–Bellman and Isaacs equations subject to a homogeneous Dirichlet boundary condition and the numerical approximation of the effective
Hamiltonian, where the
diffusion matrix is assumed to satisfy the Cordes condition. In the first part, assuming the Cordes parameter is sufficiently large, we show existence and uniqueness of $W^{2,p}$ solutions to the true
cell problem, prove homogenization under minimal regularity assumptions, and establish a quantitative homogenization result. In the second part, we propose and rigorously analyze $W^{2,p}$-conforming and mixed finite element methods for the approximation of the corrector, which are then used in the approximation of the effective
Hamiltonian. The key tool used throughout this work is Campanato's concept of near operators.
Read the full abstract ▾
Computer Vision
MARS: Systematic Multi-Level Acceleration for World Action Models
Zengyuan Zuo, Yongchang Zhang, Guangyu Zhao et al. (+4 more)
World Action Models (WAMs) have emerged as a promising alternative for embodied intelligence by jointly predicting future world states and
robot actions. However, their heavy visual encoding and iterative generative inference incur substantial latency, limiting their applicability to high-frequency closed-loop control. Existing training-free acceleration methods typically optimize a single stage, yielding limited speedups or degraded control under aggressive reuse. In this work, we systematically profile the inference overhead of WAMs and observe abundant redundancy across
Transformer computation,
diffusion denoising, and consecutive policy queries. However, the safe removal of such redundancy depends strongly on its impact on action prediction and control sensitivity. Based on these observations, we introduce MARS, a training-free and plug-and-play framework for multi-level WAM acceleration. MARS selectively removes low-impact
attention computation, adaptively accelerates
diffusion inference according to motion granularity, and speculatively reuses predicted future visual representations across consecutive queries with online verification. Together, these complementary mechanisms provide remarkable acceleration while limiting approximation error. Extensive experiments across LIBERO, LIBERO-PRO, and RoboCasa show that MARS achieves up to $4.00\times$, $3.94\times$, and $2.10\times$ end-to-end speedups, respectively, while maintaining task success rate close to the original policy. Moreover, MARS generalizes across different model backbones and across simulation and real-
robot experiments, substantially improving the efficiency–performance trade-off of WAM inference. Our code is available at https://github.com/PKU-VaLuE-Lab/MARS.
Read the full abstract ▾
All authors Zengyuan Zuo, Yongchang Zhang, Guangyu Zhao, Tianze Zhang, Biao Wu, Meng Fang, Yiwu Zhong
Data Structures and Algorithms
LOCAL LLL in $\operatorname{poly}(\log\log n)$ Rounds
Maxime Flin, Mohsen Ghaffari, Magnús M. Halldórsson et al. (+2 more)
We provide a $\operatorname{poly}(\log\log n)$-round randomized LOCAL
algorithm for the constructive Lovász Local Lemma with
polynomial criterion $pd^{c} < 1$, for a sufficiently large constant $c$. The best previous general round complexity was $\widetilde O(\log n)$. The key ingredient is a local reduction that amplifies the LLL probability exponent quadratically, while increasing the dependency radius only by a constant factor.
Read the full abstract ▾
All authors Maxime Flin, Mohsen Ghaffari, Magnús M. Halldórsson, Yannic Maus, Alexandre Nolin
Machine Learning
Masked Attention Pooling Is Invariant to Padding and Permutation: A Formal Proof in Lean
Yusuf Khaled Sadek and Enes Yilmaz
Attention-based multiple instance learning (MIL) pools a variable-size bag of instance
embeddings into one vector. In batched training, bags are padded to a common length, and the pooled output is expected not to depend on how much padding was added or on the order in which instances are stored. This expectation holds only if padded rows are removed from both the numerator and the softmax normalizer. Common implementation idioms meet it only under side conditions. Zeroing padded features alone does not work. Masking logits with $-\infty$ fails on empty bags and on nonfinite padding. Masking with a large negative constant is exact only after floating-point underflow. We define masked
attention pooling with a guarded normalizer and prove in Lean 4 with mathlib that it is invariant under any bijective reindexing of rows and under appending any finite number of masked rows with arbitrary real features and logits. We also prove that values at masked positions are irrelevant and that an all-masked bag maps to zero. The
theorems hold for arbitrary finite index types and feature dimensions. Using the jax-lean certificate pipeline, we connect these
theorems to the Jaxpr traced from the JAX kernel itself. Lean checks translation certificates for two concrete shapes, identifies the generated functions with the generic specification, and transfers both invariances to the imported Jaxpr's real-arithmetic semantics. All audited
theorems depend only on Lean's three standard axioms. The results concern ideal real arithmetic. Floating-point execution, XLA, and the JAX tracer and importer remain outside the proof.
Read the full abstract ▾
Sound
SonicWorld: Source-Centric Latent Dynamics for Spatial Audio Reasoning
Chenlong Wei, Hanling Wang, Mingjin Lou et al. (+6 more)
Dynamic spatial audio
reasoning requires a model to associate changing acoustic observations with the correct source and recover its spatial state at a queried time or interval, a challenge intensified by overlapping
speech and source motion. To study this problem, we introduce Sonic-Bench, comprising 2.8K first-order Ambisonics clips and 28.8K target-specific question-answer pairs across 480 simulated indoor scenes. The
benchmark covers localization, distance estimation, and motion
reasoning in single- and dual-source settings. We further propose SonicWorld, which integrates physical, learned acoustic, and semantic features into persistent source states through learned transitions and recurrent updates, and projects them into an Omni LLM for spatial
reasoning. Compared with Spatial-Omni on the Sonic-Bench test split, SonicWorld improves direction accuracy from 31.98% to 34.69% and reduces azimuth error from 57.22{\deg} to 48.01{\deg}. In zero-shot transfer to Spatial LibriSpeech, SonicWorld retains strong localization performance, achieving 73.98% direction accuracy and 19.29{\deg} azimuth error, compared with 27.14% and 70.74{\deg} for Spatial-Omni.
Read the full abstract ▾
All authors Chenlong Wei, Hanling Wang, Mingjin Lou, Yufan Shi, Yandong Sun, Sheldon Yu, Xiaohui Zhu, Xiaobo Jin, Yiwei Wang
Artificial Intelligence
EvoQuantLab: Training-Free Dual-Loop Evolution for Auditable Quantitative Research
Haolin Yang, Zhiqiang Qian, Chutian Chen et al. (+7 more)
Automated alpha factor discovery is critical for modern quantitative research. While large
language models (LLMs) have increasingly been integrated into quantitative workflows, existing
agent-based approaches remain highly susceptible to severe backtest overfitting. To address this challenge, we propose EvoQuantLab, a training-free, dual-loop self-evolving framework for robust factor discovery. Instead of relying entirely on LLM generation, EvoQuantLab deploys an inner genetic-programming (GP) loop that dramatically improves
token efficiency while evolving typed factor expressions under structural and diversity constraints. An outer diagnosis loop then systematically audits evidence across cycles to drive protocol-level improvements. Furthermore, our evaluation pipeline applies multi-metric validation to rigorously filter out spurious factors before deployment. Extensive out-of-sample experiments across both daily and hourly frequencies – covering equities and cryptocurrency – demonstrate the robustness of EvoQuantLab. Specifically, on daily CSI 500 and S&P 500 tasks, EvoQuantLab achieves leading annualized returns of 18.34% and 21.30%, consistently outperforming existing
agent baselines. On high-turnover hourly cryptocurrency data, EvoQuantLab delivers a 37.91% annualized return while effectively avoiding execution collapse.
Read the full abstract ▾
All authors Haolin Yang, Zhiqiang Qian, Chutian Chen, Jipeng Zhang, Zhenghao Zhu, Tangjia Deng, Jian Xie, Shuaishuai Gong, Yike Guo, Sirui Han
Computer Vision
EgoProbe: Benchmarking Long-Range and Exact Memory in Streaming Egocentric Videos
Haokai Pang, Yuqian Fu, Yifei Wang et al. (+4 more)
Egocentric
video provides a continuous first-person record of everyday activities, making it a natural foundation for wearable AI assistants. Unlike offline
video understanding, streaming systems must process observations as they arrive, while queries may refer to experiences from the distant past. Recent work has begun to explore whether information can be recalled across long temporal gaps. Yet remembering how far is only part of the challenge: recurring objects, actions, and locations also require models to remember exactly which detail belongs to which event. We introduce EgoProbe, a
benchmark that evaluates streaming egocentric
memory along these two complementary dimensions: long-range retention, i.e., how far, and event-specific recall under interference, i.e., how exact. Built on long-form egocentric
videos, EgoProbe uses an event-grounded data engine to extend recall intervals, identify related events, and construct event-grounded distractors, followed by human verification. It contains two subsets: EgoProbe-Base, which evaluates long-range recall without intervening related events, and EgoProbe-Echo, which challenges models with similar intervening events and event-grounded distractors. EgoProbe-Echo adopts coarse-to-fine multi-turn probing: the first turn evaluates coarse-grained event recall, while the second tests whether the model can retrieve the target-specific detail associated with the designated event. Extensive evaluation across diverse models reveals substantial limitations in long-range recall, with further challenges in recovering target-event details among related experiences. Even when models correctly answer coarse-grained questions, they often fail to recall the specific details of the designated event. EgoProbe exposes this underexplored failure mode and provides a testbed for advancing long-range and exact
memory in streaming egocentric
video understanding.
Read the full abstract ▾
All authors Haokai Pang, Yuqian Fu, Yifei Wang, Yujiao Shen, Tianwen Qian, Mohamed Elhoseiny, Hongbo Fu