Machine Learning
Parameter-Efficient Distributionally Robust Adaptation of Tabular Foundation Models under Subpopulation Shift
Seonghwi Kim, Sung Ho Jo and Minwoo Chae
Despite strong mean accuracy, tabular foundation models (TFMs) can perform poorly on underrepresented groups under subpopulation shift, where group proportions change between training and deployment. We propose DR-TFM, a parameter-efficient distributionally robust adaptation framework that requires no true group annotations. DR-TFM adjusts
attention to labeled context examples by fine-tuning an existing query scaling network or adding and training one, while keeping all other parameters fixed. We instantiate the framework with two robust objectives using estimated groups or source conditional distributions derived from training data. For TabPFN-3, adaptation updates only 0.016% of the pretrained model's parameters. Across five tabular
benchmarks, DR-TFM achieves substantially higher average worst-group accuracy than pretrained TFMs and the compared robust baselines without true group annotations, while maintaining competitive mean group accuracy. DR-TFM also improves average worst-group accuracy on ACS Income and across four additional TFMs.
Read the full abstract ▾
Machine Learning · Cross-listed from quant-ph
Classical Hardness of Learning Functions of Hamiltonians
Sota Hashimoto and Akinori Kawachi
Morohoshi, Nakayama, Manabe, and Mitarai proposed a physically motivated
quantum machine learning problem in which the goal is to predict quantities of the form $\operatorname{Tr}[f(H)\rho]$ from classical descriptions of a
Hamiltonian $H$ and a
quantum state $\rho$, where $f$ is an unknown function. We call this problem
Hamiltonian function learning in this paper. They constructed an efficient
quantum learning
algorithm under suitable conditions, while leaving a rigorous proof of average-case classical hardness open. In this paper, we rigorously prove the average-case classical hardness for two distribution-specific
Hamiltonian function learning problems for $f_{\cos,\pi}(\lambda)=\cos(\pi\lambda)$ and $f_{\exp,\beta}(\lambda)=e^{-\beta\lambda}$ discussed in the paper of Morohoshi et al. under the assumption of the average-case hardness of factoring random RSA
moduli. More specifically, we show that an efficient classical randomized learner under squared loss whose output hypotheses are evaluable in classical
polynomial time for either problem would yield a classical randomized
polynomial-time
algorithm for factoring random RSA
moduli.
Read the full abstract ▾
Artificial Intelligence
ReSolve: Reusing Candidate Reasoning through Selective Generative Moderation
Bangji Yang, Jiajun Fan, Hongbo Ma et al. (+6 more)
Sampling multiple solutions spends computation on intermediate deductions and unfinished arguments as well as final answers. We introduce ReSolve, a training-free inference procedure that reuses this candidate
reasoning through selective generative moderation. An answer-distribution controller invokes a model to examine existing derivations when candidates disagree or lack a parseable answer, then incorporates the generated solution into a bounded loop. Under Hybrid scoring on 130 competition-mathematics problems evaluated with two independently sampled candidate pools, ReSolve obtains 100 and 99 correct answers, compared with 91 and 92 for voting over the same four candidates, with no correct-to-incorrect changes relative to that vote in either pool. Eight-sample self-consistency obtains 94 and 96 correct answers while consuming substantially more
tokens; ReSolve uses 46.3% and 47.2% fewer
tokens in the two evaluations. A controlled ablation removes visible derivations while retaining answer keys, vote counts, and the per-state output-cap rule, reducing accuracy from 100 to 93 correct despite increasing computation. Selective and always-on Uniform moderation both solve 97 problems, while selectivity reduces moderation
tokens by approximately 54% and total pipeline
tokens by 6.2%. These results support candidate
reasoning as reusable inference computation. They do not establish an accuracy advantage over additional sampling or a distinct benefit from specialized route instructions.
Read the full abstract ▾
All authors Bangji Yang, Jiajun Fan, Hongbo Ma, Xi Zhu, Weizhi Zhang, Minghao Guo, Ye Li, Hamid Palangi, Jiaxuan You
Information Retrieval
Do Multilingual Encoders Produce Language-Consistent Semantic IDs?
Abhinav Bohra and Anuj Bohra
Semantic IDs (SIDs) compress item
embeddings into discrete code sequences used in generative
retrieval. We ask whether a
multilingual encoder is sufficient for different-
language renderings of the same product to receive
language-consistent SIDs. Using Amazon ESCI listings rendered in English, Spanish, and Japanese, we test whether translations remain close to their English source, whether residual quantization is unusually sensitive to translation-induced movement, and whether
multilingual or
language-balanced quantizer fitting improves SID agreement.
Multilingual E5 places translations measurably apart: under an English-heavy fit, a Japanese translation preserves the first SID code of its English counterpart in only 7.7% of cases, compared with 89.0% for an English rewording. Distance-matched product-directed controls produce nearly the same full-SID mismatch as translation, providing no evidence that the quantizer selectively amplifies
language directions. Balancing the fitting mixture makes codebook use more uniform but further reduces cross-lingual prefix agreement: Spanish first-code consistency falls from 28.3% to 6.6%, while an English-only fit preserves it for 67.6% of Spanish translations. These results show that
multilingual exposure and balanced codebook use alone do not guarantee
language-consistent SIDs.
Read the full abstract ▾
Artificial Intelligence
Auditing Action Settlement in LLM Agent Environments: Order, Progress, and Replay
Haotian Chen, Bowen Ye, Yuning Zhang et al. (+1 more)
Concurrent actions in large
language model (LLM)
agent environments require arbitration even when each proposal is individually valid. We implement a typed snapshot-settlement contract and audit three distinct properties: order sensitivity, useful progress, and replay consistency. Five settlement policies are tested in 28,800 exhaustive permutation trials and 2,160 scripted multistep episodes. Joint policies are spatially order-invariant conditional on fixed priorities, yet conservative rejection completes only 31.25% of
agents in a six-
agent doorway task versus 90.28% for random tickets; the paired improvement is 59.03 percentage points (95% bootstrap interval: 50.00-68.06). All policies preserve the tested spatial constraints, and priority arbitration still misses the independent small-instance optimum. A separate full-state journal audit exactly replays 156 checkpoints and rejects 1,332 constructed corruptions with a retained terminal anchor. The evidence concerns execution semantics, not human realism or long-run
fairness.
Read the full abstract ▾
All authors Haotian Chen, Bowen Ye, Yuning Zhang, Jingkun Yu
Computer Vision
The RSNA Intracranial Aneurysm (RSNA-ICA) Dataset
Maria Correia de Verdier, Rachit Saluja, Jason Sho et al. (+37 more)
Intracranial aneurysm rupture is associated with substantial morbidity and mortality, yet aneurysm detection remains challenging, particularly for small lesions and on routine non-angiographic imaging examinations. To support the development and evaluation of artificial intelligence (AI)
algorithms for intracranial aneurysm detection and localization, the Radiological Society of North America (RSNA), in collaboration with the American Society of Neuroradiology (ASNR), the Society of Neurointerventional Surgery (SNIS), and the European Society of Neuroradiology (ESNR), curated the RSNA Intracranial Aneurysm (RSNA-ICA)
Dataset. Developed for the 2025 RSNA Intracranial Aneurysm Detection Challenge, RSNA-ICA is a large, publicly available, expert-annotated
dataset comprising 7202 CTA, MRA, and MRI series from 4278 adult patients collected across 21 institutions in 12 countries spanning five continents. The
dataset includes 2566 CTA, 2166 MRA, and 2470 MRI series from patients with and without intracranial saccular aneurysms, providing substantial geographic and imaging diversity. Expert annotations indicate both aneurysm presence and location, and 178 series additionally include three-dimensional
segmentations of challenge-defined vascular locations. RSNA-ICA was used to develop and evaluate
algorithms in the 2025 RSNA Intracranial Aneurysm Detection Challenge. Of the 7202 image series, 5041 are publicly available through MIRA, while the remainder were used for challenge public and private test sets. The
dataset is freely available to the research community for noncommercial use and provides a comprehensive resource for advancing AI-based aneurysm detection across both angiographic and routine neuroimaging examinations.
Read the full abstract ▾
All authors Maria Correia de Verdier, Rachit Saluja, Jason Sho, Maryam Vabarizad, Rennie Yung-Chieh Chen, Uyen N. T. Nguyen, Mona Alrehaili, Layal Aweidah, Deniz Bulja, Wesley C. Chan, Hernan Chaves, Madhavi Duvvuri, Huseyin Ekin Ergin, Undrakh-Erdene Erdenebold, Ekim Gumeler, Mohamed Sobhi Jabal, Chin-Chi Kuo, Fatima Mubarak, Sevde Nur Emir, Scott Riley K. Ong, Johanna Ortiz, Almudena Pérez-Lara, Andreas M. Rauschecker, Shayan Sirat Maheen Anwar, Charit Tippareddy, Tam Tran, Sorawis Visrutaratna, John Mongan, Adam E. Flanders, Robyn Ball, Greg Zaharchuk, Peter D. Chang, Felipe Kitamura, Errol Colak, Luciano Prevedello, Tyler Richards, Data Contributor Group, Dataset Annotator Group, Evan Calabrese, Jeffrey D. Rudie
Computer Vision
Open Vocabulary Word Recognition From Transcribed Bangla Texts
Faias Satter and Sk. Md. Masudul Ahsan
An optical character recognition (OCR) can scan a paper and extract text using technology, making people's jobs easier. While various OCR systems are available in the software industry, finding a reliable equivalent solution for Bangla takes much work. When it comes to handwritten texts, the situation is much more unusual. Recognizing words from word images is the most critical stage in any OCR process. It is the second stage after segmenting words from text pictures. If this stage fails, the overall performance of the OCR will be poor, regardless of how well the other phases perform. This study aims to recognize words using deep learning in a handwritten Bangla word image. Three object detection models, SSD with MobileNetV2, Faster R-CNN with InceptionResNetV2, and an ensemble model of these two, have been used to train and test handwritten word images. A modified Non-Maximum Suppression has been introduced to enhance the effectiveness of the models' results. A customized
dataset of 9841 handwritten Bangla word images has been compiled, featuring diverse handwriting styles from various individuals. All three models' performances have been checked against the test
dataset, and the ensemble model has been the most impressive, with an F1-score of 92.61%. Also, at the word level, the ensemble model correctly recognizes 96.12% of the words to some extent. The system can be further improved by introducing a post-processing phase to correct errors generated by the system.
Read the full abstract ▾
Machine Learning
Does Scaling Reinforcement Learning Really Require More Training?
Bangji Yang, Jiajun Fan, Hongbo Ma et al. (+2 more)
Scaling
reasoning typically spends more compute on reinforcement learning (RL) or on inference. We show that a completed RL training history can yield policies stronger than the checkpoints visited by its optimizer. We call this policy-space scaling: expanding the deployable policy set accessible from a fixed RL history, without extending training or increasing per-query inference computation. We instantiate it with SURGE (Scaling Up RL Gradient-free via Eigenspace fusion). SURGE combines two checkpoints from the same RL run: a high-accuracy anchor and a competitive donor that generates shorter responses. It expresses both checkpoints as changes from their shared initialization, then spectrally decomposes the anchor's update to retain its dominant component and incorporate the donor's complementary component. With a fixed target for how much of the anchor update to retain, SURGE determines the block size from the weights without testing candidate policies. We evaluate two 1.5B mathematical-
reasoning histories, DeepSeek and Nemotron, and one 7B coding history, OLMo. SURGE improves
benchmark-average accuracy over both input checkpoints while using fewer
reasoning tokens than the anchor. It reaches 54.17% on DeepSeek AIME24 against a measured native maximum of 50.83%, and 83.7% on OLMo HumanEval+ against 82.8%. These gains exceed the observed training curves.
Geometric controls support the importance of RL-update structure beyond weight displacement or
token reduction alone. Each constructed model runs as a single policy. Our findings identify stored RL history as a reusable scaling resource: the capability available from a training run need not end at its best checkpoint.
Read the full abstract ▾
All authors Bangji Yang, Jiajun Fan, Hongbo Ma, Ruihan Guo, Ge Liu
Computational Geometry
Optimal Coresets for Hyperbolic Farthest-Point Queries via Ideal-Boundary Envelopes
Eunku Park
We study coresets for farthest-point queries in
hyperbolic space. Given a nonempty finite set $P \subset \mathbb{H}^D$ and $0<\varepsilon \le 1$, we seek a coreset $P_{\varepsilon} \subseteq P$ whose farthest distance from every query point underestimates that of $P$ by at most an additive $\varepsilon$ and retains at least a $1-\varepsilon$ fraction of it. For every fixed $D \ge 2$, we prove that the optimal worst-case coreset size is $\Theta\bigl(\varepsilon^{-(D-1)/2}\bigr)$. Our main
geometric ingredient is an exact reduction from
hyperbolic queries to an upper envelope on the ideal boundary. In the hyperboloid model, each input point induces a positive boundary-score function whose logarithm gives its asymptotic distance offset along geodesic rays. We define the ideal-boundary envelope as the pointwise maximum of these functions and prove that the supremum additive loss over all queries equals the maximum logarithmic gap between the input and coreset envelopes. For the upper bound, we move the minimum-enclosing-ball center to the origin and normalize the spatial coordinates, obtaining a bounded Euclidean point set whose boundary envelope is bounded away from zero. A standard Euclidean kernel then approximates all directional score maxima simultaneously, and the structure
theorem yields both guarantees. For the lower bound, a spherical packing on a fixed-radius
hyperbolic sphere, together with antipodal queries and the
hyperbolic cosine law, makes every input point indispensable, matching the upper bound even for either guarantee separately.
Read the full abstract ▾
Computers and Society
From Digital Capabilities to Non Linear Growth: The Exponential SME Framework
Dhushy Thillaivasan, Kristina Nicholls, Sathyapriya Govindarajulu et al. (+1 more)
Small and medium-sized enterprises (SMEs) face increasing pressure to navigate digital transformation, yet many struggle to convert digital initiatives into sustainable organisational capability development and growth outcomes. This paper develops the Exponential SME Framework, an integrated conceptual framework that explains how SMEs may progress from digital capability development to non-linear growth potential. Drawing on literature relating to Digital Dynamic Capabilities (DDC), digital transformation practices, organisational transformation, Exponential Organization (ExO) attributes, and SME growth, the framework synthesises previously fragmented streams of research into a coherent conceptual structure. The framework proposes that Digital Dynamic Capabilities provide the foundation for Digital Transformation Practices (DASAT), which contribute to transformations across key organisational domains, including business models, value chains, customer relationships, and organisational culture. These transformations may support the adoption of ExO-like attributes, specifically experimentation, dashboards, autonomy, and community engagement, that enhance organisational adaptability, learning, and responsiveness. Through the interaction of these organisational elements, SMEs may strengthen the conditions associated with non-linear growth potential. The paper contributes to the SME and digital transformation literature by integrating multiple streams of research into a unified framework, clarifying the relationships between capabilities, practices, organisational transformation, and growth-enabling mechanisms, and providing a foundation for future empirical research. The paper also offers managerial and policy implications for strengthening SME digital transformation and growth readiness.
Read the full abstract ▾
All authors Dhushy Thillaivasan, Kristina Nicholls, Sathyapriya Govindarajulu, Ken Mardaneh
Artificial Intelligence
Grounding Large Language Models in DSGE Simulators for Policy Generation and Forecasting
Aditya Dubey, Namah Gupta and Vinti Agarwal
Large
language models can produce economic policy responses that sound reasonable, but this does not show that their actions are consistent with economic dynamics. We test this by placing an instruction-tuned
language model inside six Snowdrop-backed dynamic
stochastic general
equilibrium (DSGE) simulators. At each turn, the model observes the economy and a change in economic discourse, selects a bounded policy action, and receives the next simulated state and an economic reward. We implement a common Python interface for repeated rollouts, persistent shocks, state cloning, and rolling-horizon simulation. This setting creates a long-horizon credit-assignment problem. Policy effects may appear several quarters after an action is taken. PPO has a learned value function that can propagate delayed reward to earlier
tokens through generalized advantage estimation. GRPO has no learned value function and instead assigns a group-relative advantage from complete rollout returns. It therefore cannot distinguish which earlier turn caused the outcome; if every rollout receives the same return, the normalized advantage is zero. We use PPO as the primary method and GRPO as a matched critic-free baseline. The experiments also test directional semantic signals, reward horizon, trajectory warm starts, cross-simulator transfer, and historically anchored pandemic and monetary-policy shocks. The objective is to judge policy actions by their simulated economic consequences rather than by plausible
language alone.
Read the full abstract ▾
Computation and Language
Counting and Min-Cost Encoding for Tokenization in Large Language Models
Shuming Shi, Xiang Zhang, Hao Yu et al. (+7 more)
Mainstream large
language models rely on a tokenizer to encode text into a
token sequence. Different tokenizers may yield
token sequences of substantially different lengths for the same text. With a fixed model architecture, shorter
token sequences correspond to lower inference time. We propose a tokenizer training approach named Counting and Filtering (CNF) and a text encoding
algorithm called Min-Cost Encoding (MCE). MCE defines a cost function over a text segment, and determines the best
segmentation by globally minimizing the overall
segmentation cost. CNF builds a raw vocabulary by directly counting valid substrings, and then constructs the final vocabulary through a filtering step based on actual
token usage when segmenting the training corpus with MCE. The CNF-MCE conbination offers several advantages over BPE, including higher
token efficiency, greater scalability, and lower dependency. Across six text categories and two vocabulary-size groups, CNF-MCE consistently achieves better compression than the evaluated BPE tokenizers. With a 250K vocabulary, CNF-MCE increases compression rate by 26% and 30% on English web text over the o200k_base and qwen250k tokenizers. Experiments scaling the vocabulary to 1M entries on English web text demonstrate sustained improvements over BPE, with a
token efficiency improvement of over 60% and vocabulary utilization rising from 52.9% to 96.9%. The MCE
algorithm does not depend on a merge list (as in BPE) or
token probability (as in UnigramLM), making it applicable to a wide range of vocabularies, including those built from BPE, UnigramLM, CNF, and others.
Language models trained from scratch at the 1.8B and 8B scales achieve comparable average performance to models using the BPE tokenizers across 11
benchmarks. These results demonstrate that CNF-MCE can improve
token efficiency significantly while maintaining competitive downstream performance.
Read the full abstract ▾
All authors Shuming Shi, Xiang Zhang, Hao Yu, Wenbo Fei, Changjian Wang, Zhan Wang, Guoqing Pang, Guangye Yu, Quan Lu, Ning Jiang
Machine Learning
Latent Information Sharing for Accelerating Federated Learning
Seungjun Lee, Ensieh Khazaei, Dimitrios Hatzinakos et al. (+2 more)
Federated learning (FL) is a communication-efficient distributed learning paradigm. However, client drift remains one of the most critical challenges, hindering the efficient training of a global model. In this study, we propose a novel latent information sharing scheme that directly mitigates data heterogeneity across clients. Our theoretical and empirical results show that sharing a small amount of hidden-layer activations significantly improves training efficiency while preserving convergence guarantees and data
privacy. Furthermore, we compare our method with existing FL approaches designed to address client drift, including FedProx, SCAFFOLD, FedPVR, FedProto, and SplitFed, and demonstrate superior model accuracy under a fixed round budget without incurring excessive communication overhead. Overall, this work presents a promising new knowledge aggregation scheme and provides a comprehensive analysis of the impact of activation sharing on
federated optimization.
Read the full abstract ▾
All authors Seungjun Lee, Ensieh Khazaei, Dimitrios Hatzinakos, Baturalp Buyukates, Sunwoo Lee
Artificial Intelligence
CortexBridge: Cortical Alignment of EEG Montages for Foundation Models
Jiazhen Hong, Xiaotian Zhou, Zihao Ding et al. (+2 more)
Electroencephalography (
EEG) foundation models are often pretrained with a fixed channel vocabulary or a limited set of montages, making transfer difficult when electrode layouts change. We propose CortexBridge, a lightweight adapter that combines
EEG features with electrode and atlas coordinates to map arbitrary montages into a shared cortical latent space. Evaluated with three frozen foundation models on five
brain-computer interface (BCI)
datasets from the Mother of All BCI
Benchmarks (MOABB), CortexBridge improves performance in 13 of 15 evaluations. The gains in balanced accuracy average 0.80% for EEGPT, 0.70% for LaBraM, and 3.26% for CBraMod, with a maximum gain of 13.02% on 12-class steady-state visual evoked potential (SSVEP) classification. Visualizations of the learned atlas representations reveal task-dependent spatial patterns, with SSVEP showing a more concentrated representation in the Yeo Visual network than auditory P300. These results establish cortical
alignment as a learnable and anatomically grounded routing mechanism from heterogeneous
EEG montages to pretrained foundation models.
Read the full abstract ▾
All authors Jiazhen Hong, Xiaotian Zhou, Zihao Ding, Kailong Wang, Yu Wu
Numerical Analysis
Sign-switched antithetic coupling in gradient random-walk methods for convection-diffusion equations
Stephen Abkin and Prabir Daripa
We propose an antithetic coupling that reduces the computational cost of gradient random-walk methods for one-dimensional convection-
diffusion equations. The methods represent the solution's spatial derivative by particles with positive or negative masses, whose cumulative sums reconstruct the solution, and model
diffusion by Gaussian displacements. The particles reorder and, for a nonlinear flux, interact. Antithetic sampling negates the displacements of a second simulation, which positively correlates the contributions of particles matched by position when their masses have opposite signs. Our coupling instead gives matched particles of opposite sign identical displacements and retains opposite displacements for equal-sign pairs. We prove that each simulation keeps the distribution of an uncoupled run as the matching changes, so the averaged solution keeps the bias of one simulation. For fixed particle configurations and matching, the coupling minimizes each matched pair's conditional variance contribution after
diffusion among all couplings with the same Gaussian marginal distributions. From the same configurations, its variance reduction over antithetic sampling at the final
diffusion stage has a closed form for any flux. For the heat equation, a martingale decomposition extends both results to each step's contribution to the terminal variance. In a Burgers' equation test, the coupling meets a tolerance for the spatially integrated mean squared error with 4 simulations, against 34 for antithetic sampling and 65 for independent sampling. In a second test, it meets a common error tolerance in about 40% less time than pairing particles only within each sign.
Read the full abstract ▾
Artificial Intelligence
AbsorbEvo: An Agentic Framework for Autonomous Inverse Design of Microwave Absorbers
Zhicheng Feng, Yubo Zhao and Xuefeng Yao
Designing high-performance microwave absorbers requires specialized expertise in electromagnetic theory, materials science and simulation programming, and entails time-consuming optimization. Here, we present AbsorbEvo, an agentic framework for autonomous inverse design that translates natural-
language performance objectives into designs verified by full-wave simulations. Its candidate
evolution strategy integrates
language reasoning, physics-based prediction and historical feedback. A large
language model proposes the directions and magnitudes of parameter adjustments based on task objectives and computational history. The system combines directed increments with global sampling to generate candidates and uses a low-cost predictive model as a physics prior to rank them. Only high-ranking designs undergo full-wave simulation. Results passing physical validity checks are used to evaluate performance and guide subsequent search. Experience from training tasks is further distilled into textual skills, which are independently validated before use in new tasks. Under identical proposal budgets on held-out AbsorbBench-36 tasks, AbsorbEvo achieved a task success rate of 79.17%, versus 25.00% for a generic
agent and 12.50% for random search. Its mean best coverage was 0.7816, compared with 0.6434 and 0.6448, respectively. By integrating
language reasoning and physics-based feedback into design decisions, AbsorbEvo provides a methodological foundation for natural-
language-driven autonomous inverse design of microwave absorbers.
Read the full abstract ▾
Computation and Language
Madeleine: Learning Involuntary Recall for Conversational Memory from Simulated Lives
Zhiyun Shi
A long-term conversational assistant must recall the right
memory at the right moment, yet the
memory that matters most is often not similar to what the user says now. Current systems recover such associations by letting an LLM reason at write or read time, at a cost of hundreds to over a thousand LLM calls per
memory bank and up to several thousand context
tokens per query. We argue that association is a learnable relevance: the pointwise mutual information of
memories under how human lives unfold. We introduce Madeleine, which learns amortized association: offline, an LLM life simulator writes simulated lives, whose cue-trigger pairs teach a query encoder a residual association on top of frozen similarity; online, it calls no LLM and plugs into any vector
memory by replacing only the query encoder. On LoCoMo-Plus under the official protocol, Madeleine (I) reaches 66.6 when plugged into HyperMem, the highest among all systems evaluated under this protocol; (II) used alone, reaches the score of HyperMem as released (52.4 vs. 52.9) with zero LLM calls and about 1/21 of its answer context; and (III) lifts T-Mem by 26.2 points, significantly outperforms the same untrained backbone inside both systems, and leaves ordinary QA intact on the 4B backbone.
Read the full abstract ▾
Artificial Intelligence
Beyond State-of-the-Art: Standardising Environmental Impact Metrics for AI Research
Lachlan McGinness, Dan Pagendam and Robert Offner
As the capabilities and ubiquity of Large
Language Models (LLMs) grow, so does their environmental footprint. Despite calls for responsible AI, the machine learning community lacks standardised practices for carbon accounting. Our automated literature review of the 5,285 papers accepted to NeurIPS 2025 reveals that reporting of environmental impact is nearly non-existent. To catalyse a shift toward sustainable AI, we define standardised sustainability metrics for evaluating model training efficiency, accompanied by simple heuristics to estimate the carbon cost of LLM inference. We implement these metrics in carbonbenchmark, a drop-in software solution for tracking and reporting emissions. Finally, to combat the pursuit of marginal accuracy gains at disproportionate environmental costs, we formalise the `Smallest Model that Achieves the Job' (SMAJ), a framework which challenges the field to prioritise computational efficiency and environmental accountability alongside traditional `State-of-the-Art' (SotA) accuracy.
Read the full abstract ▾
Computer Vision
Affine-Aligned Atlas for Canonical Gaussian Construction in Video Representation
Masaya Takabe, Hiroshi Watanabe, Sujun Hong et al. (+1 more)
Gaussian splatting has recently emerged as an efficient representation for images and
videos due to its explicit structure and fast rendering capability. Existing Gaussian-based
video representations often decompose a
video into canonical Gaussians and temporal deformation. However, when a
video contains large global motion such as camera movement, the canonical representation may become misaligned with individual frames, increasing the burden on the temporal deformation model. In this paper, we propose an affine-atlas canonical Gaussian representation, which constructs canonical Gaussians in a larger affine-aligned atlas space. Frame-wise affine transforms absorb global motion before canonical Gaussian construction, reducing the gap between the canonical representation and target frames. Since the proposed method only modifies the canonical construction stage, it can be integrated into existing canonical-Gaussian-based methods with negligible additional parameter cost. Experiments show that our method improves reconstruction quality especially for sequences with large camera motion.
Read the full abstract ▾
All authors Masaya Takabe, Hiroshi Watanabe, Sujun Hong, Tomohiro Ikai
Numerical Analysis
A higher order lattice-based method for high-dimensional numerical integration using periodization
Felix Bartel, Alexander D. Gilbert, Michael Griebel et al. (+2 more)
We present a novel numerical integration method for non-periodic functions over the high-dimensional unit cube $[0,1]^s$ by a specially crafted (unequally-)weighted quadrature rule using transformed
lattice points, with the additional option of subsampling. The method is designed for integrands whose mixed derivatives up to order $\alpha$ are square-integrable with respect to a product Chebyshev density. The ingredients are (i) periodizing the integrand, (ii) approximating the smooth periodic function by a kernel interpolant at
lattice points, (iii) integrating exactly the product of the kernel interpolant and the nonsmooth density, together with subsampling alternatives for (ii) and~(iii). With $|J|$ corresponding to the number of function evaluations, we achieve the convergence rate close to the order $|J|^{-(\alpha-1/2)}$ and $|J|^{-\alpha}\,($1.110721$)^s$, where the implied constants are independent of $s$ under favorable conditions. We can interpolate these two results to trade between the convergence rate and the growth in $s$. We provide numerical experiments to demonstrate our theory.
Read the full abstract ▾
All authors Felix Bartel, Alexander D. Gilbert, Michael Griebel, Frances Y. Kuo, Ian H. Sloan
Machine Learning
How Much Can Language Models Gain from Test-Time Computation?
Bangji Yang, Jingyuan Li, Jiajun Fan et al. (+8 more)
How much can test-time computation improve a
language model, and at what cost? Test-time scaling is widely proposed as a substitute for larger models, but existing comparisons mostly evaluate one domain at a time and rarely charge selection to the budget. We introduce SELF-POT, a
benchmark and evaluation framework that measures the test-time potential of a model across competition mathematics, competitive programming, and agentic workflows. SELF-POT separates candidate coverage from final accuracy on static tasks, tracks correctness transitions under revision, and measures protocol completion alongside task success in agentic environments. Under a unified budget rule, it compares Direct inference with parallel sampling and self-revision under fixed multiples of the Direct budget, and charges every model call, including selection and critique, in dollars. This design supports two kinds of comparison: the gain a model obtains from additional inference, and a lower-cost model with additional inference against a stronger model. Across five low-cost
reasoning models on 350 sealed tasks, with Claude Opus 5.5 Direct as the reference, the returns depend on the domain, the selection rule, and failure handling. When we replay the retained programming candidate pools, public-example selection raises correct submissions from 376 to 453 of 500 scheduled
cells while saving 12-49% of logical API cost across models, and simply retaining an available candidate when judging fails recovers 61 submissions at unchanged cost. On identical mathematics pools, judging with fallback yields 186 correct submissions versus 182 for voting, while voting saves 12-21% of logical API cost. These controlled replays show how selection and failure handling change the gains realized from the same generated candidates, and they quantify the marginal value of a model judge.
Read the full abstract ▾
All authors Bangji Yang, Jingyuan Li, Jiajun Fan, Yi Evie Zhang, Ruihan Guo, Hongbo Ma, Neil He, Chumeng Liang, Qinglong Zheng, Zhanghan Ni, Ge Liu
Computation and Language
AgSpec: Pushing the Limits of Retrieval-Based Speculative Decoding in Coding Agent Pipelines
Sumin Lee, Sukmin Cho, Seungjae Lim et al. (+1 more)
Retrieval-based speculative decoding (SD) drafts
tokens by copying continuations from existing text, which suits coding
agents that repeatedly reproduce code, logs, and earlier attempts. Yet existing methods fall short in
agent pipelines: much of the reusable text is missing from their corpora or stored in a form that differs from what the
agent emits, and their draft lengths ignore that accept length varies across
agents and drifts over turns. We present AgSpec, a framework that supplies the corpus and draft-length policies that existing
retrieval engines lack in coding-
agent pipelines. AgSpec retrieves from session, workspace, and global corpora, retaining the ongoing session trajectory and indexing opened files in the
agent's emission format. It bounds each
agent's draft length with an offline-profiled cap and adapts the length online from verification feedback. On two repository-level multi-
agent coding
benchmarks, AgSpec outperforms five
retrieval-based drafters and EAGLE-3 in most evaluated settings, raising generation throughput over autoregressive decoding up to 4.37$\times$ at batch size 1 and 4.76$\times$ at batch size 16. AgSpec also remains effective on
benchmarks without a repository or a multi-
agent pipeline, showing that its gains generalize to coding
agents broadly.
Read the full abstract ▾
All authors Sumin Lee, Sukmin Cho, Seungjae Lim, Youngjin Kwon
Computational Engineering
Names without information: Attention allocation and rent transfer in a zero-fundamental token market
Dingding Cao, Han Wang, Yujing Zhong et al. (+3 more)
Asset names are associated with investor trading and asset prices, but where names and issuer quality are formed jointly, information, preference and
attention-coordination explanations are difficult to distinguish. We study a
token launchpad on which
tokens issued under the default template use the same contract code, have a fixed supply and carry no cash flows, while names can be registered at almost no cost, cannot be verified and may be reused. Using all 458,174 default-template
tokens launched from February to June 2026 and a sample split by creator entity fixed in advance, we find that the share of
tokens attracting an outside buyer rises from 34.9% to 52.8% across name-appeal deciles, but within creator and creation minute the effect of appeal is small and does not replicate in the validation sample. Conditional on early capital inflow and creator fixed effects, the residual effects of names on migration, peak
market capitalization and post-peak drawdown are statistically equivalent to zero, and buyers who follow appealing names earn no economically meaningful premium. The same name attracts less capital with each reuse, names whose first
token draws more capital are copied sooner, and competition over names mainly transfers wealth among buyers.
Read the full abstract ▾
All authors Dingding Cao, Han Wang, Yujing Zhong, Xian Pan, Rizwan Akhtar, Wei Yang
Robotics
Extreme Length Generalization in a Compact Recurrent Architecture for One-Shot Exploration
Izen Thornton, Aaron Shey and William Su
Autonomous
robots on one-shot missions run over horizons far longer than the trajectories seen during training, under a fixed onboard compute budget. We present FRANK, a 507K-parameter recurrent architecture that combines tau-gated recurrent modules, content-addressable
memory, and a feedforward reflex pathway. We evaluate it against recurrent, state-space, and reduced modular baselines at matched parameter count on four algorithmic sequence tasks, trained at length 5-20 and evaluated out to two million
tokens. At 100,000x the maximum training length, 6 of 10 FRANK seeds retain exactly 100.0% accuracy, while none of the 50 baseline configurations does, five architectures at ten seeds each with none left incomplete (Fisher exact, two-sided p = 4.2E-6. Targeted lesions across the four tasks yield four distinct component-reliance profiles, consistent with task-dependent allocation across the recurrent,
memory, and reflex pathways. Separately, a FRANK policy trained in simulation drives a physical ground vehicle to commanded waypoints through obstacles without teleoperation.
Read the full abstract ▾
Robotics
MASkillBlender: Decentralized Whole-Body Coordination for Multi-Humanoid Loco-Manipulation via Skill Blending
Yifan Hu, Luhang Hong, Mingkang Long et al. (+5 more)
Coordinated multi-
humanoid loco-manipulation is promising yet challenging due to high-dimensional whole-body control, decentralized decision making, and scalability. While recent reinforcement learning methods have improved single-
humanoid whole-body control, extending them to the multi-
humanoid setting remains nontrivial and often requires substantial reward engineering or task-specific design. We propose MASkillBlender, a general multi-
agent reinforcement learning framework to achieve decentralized multi-
humanoid whole-body coordination. By learning a shared decentralized high-level policy over reusable pre-trained single-
humanoid skills, MASkillBlender enables coordinated behaviors using only task-level rewards, without requiring task-specific motion references. To improve learning efficiency, we further introduce a permutation-based data augmentation strategy for homogeneous multi-
humanoid systems, and theoretically show that the permuted samples preserve the policy-gradient direction of the original samples under the homogeneous Markov game formulation. We evaluate MASkillBlender on multiple multi-
humanoid coordination tasks across two
humanoid embodiments. Simulation results demonstrate that the proposed framework consistently achieves strong task performance and enables coordinated behaviors across different tasks and
humanoid embodiments.
Read the full abstract ▾
All authors Yifan Hu, Luhang Hong, Mingkang Long, Danning Wang, Chengfeng Jia, Rong Su, Junjie Fu, Guanghui Wen
Computer Vision
MVDG: Efficient Multi-view 3D Disambiguation on Unconstrained Real-World Images
Hanyuan Xiao, Gonglin Chen, Haolin Xiong et al. (+3 more)
Illusory matches between distinct yet visually similar 3D surfaces–doppelgangers–remain a fundamental obstacle for large-scale, in-the-wild 3D reconstruction and visual localization. Prior work mitigates this issue with pairwise classifiers, but this design limits multi-view contextual
reasoning and incurs O(n^2) inference complexity for downstream structure-from-motion (SfM). We present MVDG, a scalable multi-view disambiguation framework built on the 3D foundation model VGGT, which jointly reasons over an arbitrary number of multiview images. By incorporating 3D-aware multi-view features, our method reduces dependence on pairwise comparisons by encoding and decoding views in a single pass. We further observe that direct multi-view fine-tuning of VGGT can be unstable under noisy supervision; motivated by label ambiguity in Doppelgangers, we construct a pseudo-pairwise training set from AerialMegaDepth and show that fine-tuning on sampled subsets yields stable optimization and strong generalization to held-out scenes. Finally, because full SfM evaluation (even with faster pipelines such as GLOMAP) remains expensive, we process a pseudo-pairwise
dataset for efficient validation; we derive a predictive relationship between regular SfM metrics and the classification accuracy on this pseudo-pairwise test. Experiments show that our method achieves comparable pairwise accuracy while improving both SfM accuracy and inference speed over baselines.
Read the full abstract ▾
All authors Hanyuan Xiao, Gonglin Chen, Haolin Xiong, Wenbin Teng, Haiwei Chen, Yajie Zhao
Artificial Intelligence
YouRA: A Persistent-State Architecture for Evidence-Traceable Autonomous Research Agents
Yoonkyu Woo, Woojin Lee and Jin-Xia Huang
End-to-end research
agents can now produce complete scientific papers, yet manuscript claims often diverge from executed experiments. This gap is structural: research state, failure histories, and claim-evidence
alignment are not maintained as persistent, verifiable state across long-horizon pipelines. We present YouRA (Your Research
Agent), an architecture for stateful, evidence-traceable autonomous research. YouRA preserves research state, execution evidence, and failure history across the research trajectory by integrating three components: a Verification State Architecture (VSA) that tracks hypotheses, gates, and evidence pointers; an Independent Controller that turns state and reflection records into lifecycle, recovery, and debate/review control while separating control from execution; and Stateful Reflection that logs failures as structured lessons and routes recovery through bounded repair, redesign, or reset. On MLR-Bench's predefined ten-task end-to-end subset, YouRA improves over both MLR-
Agent and AI Scientist V2 on scalar Overall across all three matched backbones. An automated diagnostic using MLR-Bench's
hallucination taxonomy reports intersection/union counts for four fact-based failure types, and data-provenance diagnostic shows more real-data-based outputs. Ablating each of the four components (the VSA, the Independent Controller, MCP tool access, and reflection-guided recovery) supports their separable contributions. Removing either core-state component drops YouRA below the full system. Code: https://github.com/PrayPrey/Your-Research-
Agent.
Read the full abstract ▾
Machine Learning
Dataset Identity, Not Novelty: The Source of an Inflated OOD Detection Gain
Donghoon Lee and Shinjin Kang
A post-hoc out-of-distribution (OOD) detector reads the activations of a trained classifier and returns a score. It fits that score on in-distribution data, and the
benchmarks that evaluate it supply a second piece of OOD data for the fitting itself. Some detectors tune a constant on it. Others fit a direction in feature space or train a flexible combiner and report the number that it reaches as the gain that is still available. Every such fit is validated on held-out samples of the same OOD
dataset. That check rules out memorizing individual images. It says nothing about a fit that has instead learned which
dataset it is looking at, and a direction that recognizes one OOD
dataset rather than novelty passes it perfectly. The detector that a practitioner installs meets OOD data from a source that nobody fitted it on, so the difference decides what the reported number is worth. We measure it by holding out the whole OOD
dataset rather than a sample of it, and we call that gap the inflation. We read it across a range of combiners on ImageNet and CIFAR-100 backbones. Most of the gain that the usual protocol reports turns out to be
dataset identity rather than novelty. The size of the fit does not move what survives, so the effect is not ordinary overfitting. The share depends instead on whether the input exposes class identity, and two controls that vary that property alone separate the inflation on every backbone of both
benchmarks. A closed form accounts for the effect and computes it from the fitting rows, so a practitioner can tell which fits will inflate without running the hold-out protocol. One of these fits survives, namely the single constant that the field already picks on a designated validation
dataset. Anything above it reports a gain that the hold-out protocol does not return, and on one
benchmark what survives falls while what is reported climbs.
Read the full abstract ▾
Robotics
OrbitTAMP: Grounding Language Models for Task and Motion Planning in Spacecraft Rendezvous
Yuji Takubo, Daniele Gammelli, Marco Pavone et al. (+1 more)
Spacecraft rendezvous and proximity operations (RPO) are currently planned through an expertise-intensive process in which engineers translate high-level operational intent into safe, dynamically feasible trajectories, creating a bottleneck to scalable operations. Large
language model (LLM)-based
agents could offer an intuitive interface for this process, although their outputs are not inherently grounded in orbital dynamics, operational constraints, or the structure of admissible spacecraft maneuvers. To exploit their semantic
reasoning while ensuring the generated plan's physical validity, this paper presents a hierarchical framework for spacecraft task-and-motion planning (TAMP) that grounds LLM
reasoning in a graph of reusable behaviors and domain-specific planning modules. Within this framework, a pretrained LLM maps a natural-
language command to a partial mission specification. The associated planners then resolve unspecified decisions within the admissible operational space. Finally, trajectory optimization converts the completed mission specification into a dynamically feasible trajectory. Numerical experiments demonstrate that this architecture substantially improves intent recovery over direct LLM generation, achieving 98% exact recovery of partial mission specifications across all evaluated splits when backed by frontier LLMs. Additional test-time-compute experiments show that, for a compact 9B model, verifier-guided revision increases exact recovery from 75% to 88%, while broader behavior-plan search independently improves selection among admissible trajectory realizations. Overall, these results establish a scalable and auditable foundation for
language-driven agentic planning of spacecraft RPO.
Read the full abstract ▾
All authors Yuji Takubo, Daniele Gammelli, Marco Pavone, Simone D'Amico
Computer Vision
Ego2Act: Evaluating Goal-Directed Manipulation in Egocentric Video Generation
Patrick Amadeus Irawan, Iskandar Muda Rizky Parlambang, Rava Maulana et al. (+10 more)
Video generation models are increasingly being explored as world simulators for
embodied planning and learning. To do so effectively, these models must not only generate visually appealing frames, but also predict how environments dynamically evolve when executing goal-directed actions. While evaluating these capabilities is crucial, existing
benchmarks focus mainly on single short actions or step-by-step instructions. This leaves multi-step physical
reasoning underexplored, especially in
egocentric video generation that requires planning to simulate proper execution to accomplish high-level goals by carrying out multiple real-world manipulations. We introduce Ego2Act, a goal-directed
benchmark featuring 2,640
videos from 110 real-world tasks across day-to-day settings, varying object clutter and multi-step complexity. Given an initial scene image and a high-level goal, Ego2Act evaluates whether
video generation models can produce realistic
egocentric videos of a hand manipulating objects to carry out the task. To support scalable evaluation, we also introduce Ego2ActJudge, a reference-free evaluation pipeline that achieves better task completion and physics plausibility evaluation
alignment with human consensus compared to relevant baselines. Our findings reveal that models' generated simulations often skip or partially execute steps, leaving later steps missing dependent states, which leads to unfulfilled goal. Furthermore, models consistently fail at fine-grained physical dynamics, particularly during complex object manipulation and persistent world modeling. We hope Ego2Act provides a rigorous testbed for advancing
video models toward physically plausible, goal-directed simulation.
Read the full abstract ▾
All authors Patrick Amadeus Irawan, Iskandar Muda Rizky Parlambang, Rava Maulana, Qinrong Cui, Erland Hilman Fuadi, Zayd M. K. Zuhri, Nanda Ryaas Absar, Ahmed Elshabrawy, Wilfried Ariel Mulyawan, Shoubin Yu, Yue Zhang, Mohit Bansal, Alham Fikri Aji