Artificial Intelligence
Verifiable Visual Rewards Transfer from Synthetic Scenes to Natural Prompts
Shuyue Stella Li, Xiaochuang Han, Yulia Tsvetkov et al. (+1 more)
Precise instruction following in image generation, such as satisfying object counts and spatial relations, remains an open challenge at least in part because it is learned using unreliable reward models such as object detectors and
vision-
language models. We introduce Verifiable Visual Rewards (VVR), the first framework for programmatically verifiable image rewards, and show that training on it generalizes to natural
prompts. Each VVR task is a scene of
geometric objects and relations among them, from which we derive both the
prompt and a deterministic verifier, so tasks can be generated in any number and at any chosen complexity. We release VVRBench, with 10,000 tasks over 32 constraint types, and VVRBench-Challenge, with 720 more complex tasks; the strongest model we evaluate—GPT-Image-2.5—solves 21.4% of VVRBench-Challenge. Using VVR scores as rewards for reinforcement learning (RLVVR) raises the accuracy of Stable
Diffusion 3.5 Medium on VVRBench from 2.8% to 28.3% and demonstrates consistent easy-to-hard generalization. These gains extend to out-of-domain
benchmarks, and mixing VVR into existing objectives further improves overall performance and human preference, motivating the adoption of VVR into standard image generation post-training recipes.
Read the full abstract ▾
All authors Shuyue Stella Li, Xiaochuang Han, Yulia Tsvetkov, Luke Zettlemoyer
Distributed Computing
GPUPhysBench: Benchmarking Coding Agents for Correct and Efficient GPU Physics Simulation
Yuchen Sun, Jinjin He, Sinan Wang et al. (+1 more)
Writing fast GPU code for physical simulation is difficult: implementations must preserve numerical accuracy while handling irregular data access, synchronization, and iterative solvers. We introduce GPUPhysBench, a
benchmark of 50 tasks testing whether coding
agents can meet these demands. Tasks cover fluids, deformable solids, and granular materials, from individual simulation operators to complete simulators.
Agents write, compile, test, and optimize GPU code with access to a NVIDIA GPU under fixed time budgets. We report pass rates and runtime performance relative to expert-optimized reference implementations. In a single-attempt evaluation of six frontier model-harness pairs, the two strongest pass all 50 tasks, but even the fastest reaches at least 0.9 the reference speed on only 22% of them, and no submission is more than 5% faster than the reference. The largest gaps arise in collision detection, constraint solving, and iterative solvers. GPUPhysBench brings physical simulation workloads to coding-
agent evaluation, testing both the ability to implement numerical methods correctly and the ability to make them run efficiently.
Read the full abstract ▾
All authors Yuchen Sun, Jinjin He, Sinan Wang, Bo Zhu
Computer Vision
RT-Super: Learning Tumor Segmentation from Longitudinal Images and Reports
Pedro R. A. S. Bassi, Wenxuan Li, Hanxue Gu et al. (+11 more)
Multi-tumor
segmentation is important for early cancer detection and allows radiologists to visualize, verify, and understand AI predictions. However, tumor
segmentation masks are expensive, time-consuming, and unavailable for many tumor types in public data. Instead, hospitals have vast, readily available data that can guide
segmentation: radiology reports, longitudinal images, and multi-phase images. We use this readily available data to substitute for tumor masks in training AI for tumor
segmentation. To this end, we propose a new architecture, RT-Super. It has a teacher network, which analyzes the patient's longitudinal images and reports to create high-quality tumor masks. These masks train a student network, which sees a single image and no report. At inference, when longitudinal images and reports are unavailable, we use the student. RT-Super uses a new CNN-
Transformer architecture and novel Consistency Losses that exploit tumor location consistency across longitudinal images. We train RT-Super to segment esophagus, uterus and spleen tumors, which have few or no public masks. Even without training masks, RT-Super can segment these tumors and surpass public AI models. Overall, we demonstrate that learning from longitudinal images, multi-phase images, and reports can overcome mask scarcity and advance multi-cancer detection and
segmentation. Code: https://github.com/MrGiovanni/RT-Super
Read the full abstract ▾
All authors Pedro R. A. S. Bassi, Wenxuan Li, Hanxue Gu, Jieneng Chen, Xinze Zhou, Zheren Zhu, Sezgin Er, Ibrahim E. Hamamci, Bjoern H. Menze, Gulhan E. Akan, Kang Wang, Yang Yang, Alan L. Yuille, Zongwei Zhou
Numerical Analysis
Isogeometric multi-patch preconditioner for time-dependent electromagnetic problems
Bernard Kapidani, Gabriele Loli, Giancarlo Sangalli et al. (+2 more)
We build upon recent developments in high-order spline-based
geometric methods for the three-dimensional initial boundary value problem of Maxwell's equations. Previous schemes were limited to single-patch geometries. To address the computational challenges associated with inverting mass
matrices in multi-patch settings, we extend existing techniques for 0-forms mass and stiffness
matrices to 1-forms mass
matrices. Our approach leverages the tensor-product structure of spline spaces to construct a spectrally equivalent preconditioner for the 1-forms mass
matrices. Specifically, we design an efficient preconditioner for single-patch domains that is robust with respect to both mesh size and spline degree. In the multi-patch case, this methodology is extended by integrating the single-patch preconditioner with an additive Schwarz approach, ensuring robustness and scalability with respect to the number of patches. We analyze the computational complexity of the proposed preconditioner and validate its robustness and efficiency through comprehensive numerical experiments.
Read the full abstract ▾
All authors Bernard Kapidani, Gabriele Loli, Giancarlo Sangalli, Mattia Tani, Rafael Vázquez
Machine Learning
Bounding Retraining Equivalence and the Deletion Floor in Materials Machine Unlearning
Can Polat, Mustafa Kurban, Erchin Serpedin et al. (+1 more)
In materials machine learning, closely related retained structures can sustain accurate property predictions even after removing a specific record, rendering post-deletion prediction error an ambiguous metric for machine unlearning. To resolve this ambiguity, we define the deletion floor as the expected target loss under a specified retraining procedure at the deleted request. Standard indistinguishability constraints yield a sharp interval bounding an update's target loss around this baseline reference. Theoretically, a conditional neighbor bound links a low deletion floor directly to retained fit, prediction regularity, and local label agreement, while an exact ridge identity isolates residual fit from the prediction change induced by record deletion. Empirically, controlled redundancy sweeps show an $\approx 8\times$ drop in median normalized retraining loss when one retained relative remains after deletion. Across two distinct fitting regimes in a paired Materials Project study, the lower-floor regime also exhibits a larger prediction change on more than 50% of the shared requests. Systematic comparisons against approximate updates and the original model decouple deliberate target suppression from preserved overall model utility. Consequently, request-level unlearning evaluations should report reference loss, prediction change, and retained utility together, interpreting post-deletion accuracy against what retraining itself leaves behind.
Read the full abstract ▾
All authors Can Polat, Mustafa Kurban, Erchin Serpedin, Hasan Kurban
Machine Learning
DR-net-Mamba: Selective State-Space Modeling for Long-Range ECG Time-Series Denoising
Basile Morel, Samuel Ruiperez-Campillo, Andreas P. Streich et al. (+2 more)
Electrocardiogram (ECG) recordings are corrupted by non-stationary noise sources that degrade diagnostic reliability, particularly in ambulatory and long-duration recordings. Deep learning denoisers exist, but convolutional architectures are limited by their receptive field,
transformer-based models scale quadratically with sequence length, and
diffusion-based approaches incur prohibitive inference cost. We propose a Mamba-augmented model that inserts selective state-space blocks at the convolutional bottleneck, combining local feature extraction with long-range temporal modeling at linear complexity. We comprehensively evaluate the proposed model with respect to reconstruction fidelity, noise robustness, recording-length scaling, and downstream diagnostic classification across over 40 pathology classes. On synthetic and real
datasets, our model achieves the highest SNR and lowest RMSE, with the Mamba advantage increasing with sequence length and in low-SNR regimes. On classification with two independent classifiers, the proposed Mamba-based models achieve the best macro AUROC among all denoisers and improve over their convolutional base models. Calibration is more nuanced and classifier-dependent: denoising improves Binary Cross-
Entropy and Brier score on Inception1D but often fails to beat the noisy input on ResNet1D-Wang, and the lead-specific Mamba variant is the only denoiser to improve both calibration metrics over the noisy baseline on both classifiers. Per-class analysis reveals a morphology-dependent benefit: Mamba substantially improves ST/T-change diagnoses, which depend on broad, context-sensitive waveforms.
Read the full abstract ▾
All authors Basile Morel, Samuel Ruiperez-Campillo, Andreas P. Streich, Julia E. Vogt, Thomas Hofmann
Cryptography and Security · Cross-listed from quant-ph
Succinct Arguments for QMA from Collapsing Hash Functions
James Bartusek and Giulio Malavolta
We prove the existence of succinct arguments for QMA, assuming only the existence of collapsing hash functions. This is the first scheme that relies only on unstructured “Minicrypt” assumptions, which are not known to imply public-key encryption. Our main technical contribution is a
quantum-succinct claw-state generation protocol that allows us to bootstrap a small number of
quantum correlations into an arbitrarily large number of claw-state correlations, using classical communication only. This improves upon the work of [Zhang, STOC 2021], having better round complexity, a proof in the standard model, and being overall much simpler. This yields a
quantum-succinct blind delegation of
quantum computation protocol from one-way functions, which we plug into the communication-compression compiler of [Bartusek, Liu, and Malavolta, EUROCRYPT 2026] to obtain succinct arguments for QMA.
Read the full abstract ▾
Computation and Language
Which the Eye Fears: Writing with Read-Blindness Explains Massive Activations in Transformers
Swagatam Mukhopadhyay, Vishal Vivek Saley, Vraj Parikh et al. (+1 more)
Massive activation features (MAs) in
Transformers are extreme-value residual-stream features that persist across layers despite the model's ability to suppress them. Why do they survive? Our investigation using an operator-level mechanistic analysis of
attention and feed-forward (FFN) blocks reveals that these blocks systematically ignore MA coordinates while reading, but not while writing; creating a read-write asymmetry that blocks corrective feedback while allowing continued accumulation. We find that both
attention and feed-forward layers have this read-blindness, and contribute to the emergence and persistence of MAs. To validate prior work that hypothesized that FFN's amplification abilities is the primary reason for MAs (Sun et al., 2026), we analyze the model checkpoints during learning. Contrary to our expectation, read-blindness emerges before FFN amplification, suggesting that it acts upstream in the MA mechanism. We further contribute gradient analysis to link this behavior to surprising asymmetries in the loss landscape, concluding that the model actively maintains this read-blindness. Finally, we find that removing read-blocking at different locations induces compensatory shifts elsewhere, but MAs still persist.
Read the full abstract ▾
All authors Swagatam Mukhopadhyay, Vishal Vivek Saley, Vraj Parikh, Mausam
Machine Learning
SANTA++: Sampling Attention through Representative Keys
Kyle Lee, Christian Z. Pratt, Ruoyu Fang et al. (+4 more)
Attention often concentrates on a small subset of
tokens in the context, but which subset matters changes from one query to the next. To exploit this changing structure, we introduce SANTA++, a training-free
stochastic attention method that uses representative keys for
memory-efficient selection without scanning the entire key-value (KV) cache. Cached keys are organized into teams, and the query scores one representative from each team to decide which teams to sample. We compute exact
attention scores within the sampled teams and reweight each team's contribution by the inverse of its inclusion probability. This importance sampling correction estimates
attention over the full cache, with a sampling budget that lets us trade
memory reads for accuracy. Remarkably, with 32 or 64 sampled teams, SANTA++ uses 16% to 22% of dense
attention's KV reads and retains 94% to 99% of the dense-
attention baseline's scores on LongBench v2 and HELMET's
retrieval-augmented generation subset, and 85% to 91% on RULER, with Qwen2.5-7B-Instruct at 32K context. With 31 sampled teams, our GPU implementation delivers a $1.69\times$
attention speedup over the dense FlashAttention baseline at 32K context. By reducing the number of cache entries read, SANTA++ in principle complements architectures with compressed KV representations, such as multi-head latent
attention. Our kernels are available at: https://github.com/OPUSLab/santapp-kernel-demo.git.
Read the full abstract ▾
All authors Kyle Lee, Christian Z. Pratt, Ruoyu Fang, Heekyung Lee, Avinash Lohitsa, Ryan Modafe, Kerem Y. Camsari
Machine Learning
Arbitrary-Accuracy Neural Approximation with Optimal Neuron Count and Near-Optimal Bit Complexity
Zilan Cheng, Li-Lian Wang and Zhongjian Wang
We study the minimum number of hidden
neurons required for arbitrary-accuracy approximation of multivariate Hölder-continuous functions on $[0,1]^d$ and the associated encoding complexity. For $d\geq 2$, we construct a fixed, explicitly defined activation function for which a closed-form network with two hidden layers of widths $d$ and $1$ achieves arbitrary accuracy in the uniform norm. We prove that $d+1$ is the exact minimum total number of hidden
neurons among standard feedforward networks with locally integrable activations and affine outputs. We further give a simpler construction using a single elementary activation that combines the floor and exponential functions. This construction requires three hidden layers of widths $d$, $1$, and $2$, only two
neurons above the minimum. If a skip connection is allowed, widths $d$, $1$, and $1$ suffice. These constructions use explicit grid addressing and integer encoding of quantized function values. For a bounded $\alpha$-Hölder class, they require $O(\varepsilon^{-d/\alpha}\log(1/\varepsilon))$ bits, matching the metric-
entropy lower bound up to a logarithmic factor.
Read the full abstract ▾
Computation and Language
Can LLMs Value the Right Evidence? Evidence-Value Misalignment in Dynamic Medical Diagnosis
Kehua Feng, Yunsheng Lu, Yitong Qiao et al. (+5 more)
A correct diagnosis reached from insufficient or misleading evidence can pose a clinical hazard, yet outcome-based accuracy may reward such lucky guesses. We call this mismatch between diagnostic decisions and the value of available evidence Evidence-Value Misalignment (EVM). To disentangle evidential grounding independently from diagnostic accuracy, we introduce MedEVM, a dynamic benchmarking environment comprising 1,050 cases across 24 disease systems. Observations arrive turn by turn, requiring models to continuously calibrate its decision by deciding whether to wait for more evidence or submit a diagnosis. Across 9 LLMs, four interesting patterns are observed. (1) Miscalibrated evidence tracking. Making a diagnosis often fails to calibrate evidence sufficiency, even in more capable models, and even worsens in
reasoning mode. (2) Misaligned diagnosis submission. Confidence in the correct diagnosis often fails to ensure timely submission despite sufficient evidence. (3) Evidence order matters. Reordering the same evidence changes diagnoses even when model confidence remains similar. (4) Misleading evidence remains influential. Added misleading evidence redirects diagnoses even after prior evidence becomes sufficient. We further verify that EVM predicts errors and that preventing premature submission improves accuracy. These findings motivate Evidence-Verified Diagnosis Harness (EVD-Harness). It decouples diagnosis generation from submission through an offline Contrastive Diagnostic Wiki and three online control stages, namely observation management, proposal and witness verification, and diagnosis submission control. Across five LLMs, EVD-Harness improves accuracy by 12.0–51.1 percentage points while mitigating EVM-related failures. Our results demonstrate that verifying evidential support before submission can make diagnostic decisions more reliable.
Read the full abstract ▾
All authors Kehua Feng, Yunsheng Lu, Yitong Qiao, Tiantian He, Lei Liu, Yue Shen, Jian Wang, Jinjie Gu
Artificial Intelligence
RIDE: Reference-Anchored Inference-Time Diffusion Editing for Scaffold Hopping
Ruoxi Gao, Frazier N. Baker, Trieu Nguyen et al. (+1 more)
Scaffold hopping is a critical task in drug discovery, which seeks to discover new, structurally distinct molecules that share key functional groups and similar 3D shape with a reference binding ligand. Existing
diffusion-based scaffold hopping methods formulate the problem as conditional generation of scaffolds given the functional groups. However, they lack a principled mechanism to jointly enforce 2D structural novelty and preserve the 3D shape of the reference ligand. Here, we introduce RIDE, a Reference-anchored Inference-time
Diffusion Editing framework for scaffold hopping. RIDE recovers the reference
diffusion noise trajectory conditioned on the binding pocket and functional groups, selects an optimal trajectory segment for editing via noise perturbation, and conducts a value-guided scaffold sampling to generate new scaffolds. Extensive experimental results demonstrate that, compared to baselines, RIDE consistently generates scaffolds with lower 2D similarity and higher 3D similarity to the reference, with an average improvements of 11.7% and 7.3%, respectively. Further analysis reveals that RIDE can accommodate various reward functions, and can preserve 3D similarity even when this is not explicitly included in the reward. Two case studies illustrate RIDE's ability to generate distinct scaffolds with different structures and properties, and its ability to introduce substantial 2D variation while maintaining very high 3D similarity. RIDE is publicly available at https://anonymous.4open.science/r/RIDE-C8A0.
Read the full abstract ▾
All authors Ruoxi Gao, Frazier N. Baker, Trieu Nguyen, Xia Ning
Machine Learning · Cross-listed from stat.ML
Elicitation and Decision Geometry in Single-Index Bandits
Sakshi Arya and Cheng Soon Ong
We study two-arm contextual bandits with arm-specific single indices and a shared unknown monotone link. Monotonicity makes the optimal action depend only on the contrast between the index directions, hence arm-specific reward functions need not be estimated. We introduce Natural Boundary Learning (NBL), a greedy procedure that uses a sequential Stein contrast to learn the optimal boundary directly, without estimating the reward functions or the common link. We characterize the local Riemannian dynamics of NBL through a decision stability coefficient balancing arm separation, link geometry, and the context distribution. We show that this stability is connected to the elicitation geometry of the underlying convex potential. Under local decision stability, NBL contracts toward the optimal boundary and achieves $O(\log n)$ expected regret. Numerical experiments illustrate the predicted stability regimes and compare NBL with a parametric greedy
benchmark under link misspecification.
Read the full abstract ▾
Machine Learning
Cartridges++: KV Cache Compression without Off-Context Derailment
Sonia Laguna, Joao Monteiro, Marco Cuturi et al. (+2 more)
Serving long documents to a Large
Language Model (LLM) repeatedly is expensive: computations grow with context length, and the
memory footprint of the key-value (KV) cache balloons. Compressed KV (CKV) representations aim to mimic the cache of a document and are typically computed once and for all, ahead of inference time. Methods to obtain CKVs range from drop mechanisms that reduce their number of columns, to learned approaches. Among the latter, Cartridges have emerged as a leading compression method, learning compact KV representations through
distillation on relevant Q/A pairs. While existing evaluations focus primarily on whether Cartridges and other CKVs yield approximately similar responses to document-related, on-context queries, we investigate the crucial deployment question of whether they can handle off-context queries, something the native KV representation is particularly good at, thanks to the mechanics of
attention. We observe a fundamental trade-off: while Cartridges perform better for on-context queries, heuristic-variants preserve better the original LLM's ability to operate off-context. We measure this through their capability to avoid context contamination in their response, retain general knowledge, and follow instructions. We propose Cartridges++, simple modifications to cartridges that retain off-context abilities at small or negligible cost. The router variant decides at inference time whether the query should use the learned long-context
memory, while the data-mixing variant allocates a small fraction of training Q/As to queries outside the reference long document. Our study shows that assessing CKVs on document utility alone can mask substantial degradation in broader model capabilities, yet those issues can be fixed with benign changes to CKV inference or training.
Read the full abstract ▾
All authors Sonia Laguna, Joao Monteiro, Marco Cuturi, Pierre Ablin, Eleonora Gualdoni
Machine Learning
Attention Graphons: A Graph Limit Perspective on Graph Transformers
Caio F. Deberaldini Netto, Moshe Eliasof and Luana Ruiz
Graph
Transformers produce, for each
attention head, a dense $n\times n$
matrix of learned pairwise interactions. We ask a fundamental question: do these
attention-induced graphs converge to a stable limit object as $n$ grows, or does the learned interaction pattern remain unstructured and size-dependent? We answer this using dense graph limit theory, treating each
attention matrix as a finite sample from an underlying kernel—an
attention graphon—and studying concentration around this limit under the cut-distance. We derive a worst-case variance bound requiring no assumptions on the graphon, and a sharper regularity-aware bound based on nonparametric estimation theory. To operationalize the theory, we propose a canonicalize-then-block-average pipeline for estimating
dataset-level
attention graphons, and a variance-based diagnostic for testing whether
attention admits a stable continuum description. Experiments across multiple graph
benchmarks show that learned
attention stabilizes to
dataset-specific graphon structure on several
datasets; that empirical cut-distance and cut-norm variance decreases with $n$ consistent with our bounds; and that
attention graphons transfer to larger graph sizes with error decreasing in $n$.
Read the full abstract ▾
Robotics
CollisionSplatting: Collision-Aware Motion Planning in 3DGS Scenes with Image-Conditioned Objectives and Adjustable Conservatism
R. Khorrambakht, Joaquim Ortiz-Haro, Stephan Weiss et al. (+1 more)
Incorporating dense visual information into motion planning remains challenging, as
geometric planners rely on abstracted scene representations that discard visual richness, while learned visual models often lack
geometric interpretability and computational efficiency. This paper introduces CollisionSplatting, a simple, modular, GPU-accelerated, probability-inspired distance metric with tunable conservatism that operates directly on standard 3D Gaussian Splatting (3DGS) scenes. When combined with learned image-conditioned reward functions, this metric enables joint
geometric and visual planning by unifying collision-aware costs with image-space objectives. We integrate the metric into GPU-accelerated Model Predictive Path Integral (MPPI) and Rapidly-Exploring Random Tree (RRT) planners, and show on-par or better collision-classification performance compared to representative baselines while achieving substantially higher collision-checking throughput and significantly lower VRAM usage. Finally, we demonstrate the effectiveness of our metric in real-world
vision-guided
navigation and manipulation tasks, highlighting 3DGS as a practical bridge between rich perception and real-time motion planning.
Read the full abstract ▾
All authors R. Khorrambakht, Joaquim Ortiz-Haro, Stephan Weiss, Ludovic Righetti
Artificial Intelligence
From cacophony to hierarchy: a principled framework for assessing AI consciousness
Shamil Chandaria, Arvo Muñoz Morán, Fernando Rosas et al. (+11 more)
The question of AI consciousness is one of the most urgent pre-emptive problems in philosophy and computer science, yet progress is hampered by a cacophony of competing theories that often talk past each other. Separating the hard problem from the mapping problem allows the deepest metaphysical disagreements to be set aside: granting that experience supervenes on a system's organisation, the tractable question becomes at which grain of description that supervenience base sits. We extend Marr's three levels of analysis into a five-level hierarchy of functional descriptions (behavioural, computational, intrinsic causal-structural, organismic, and organism-environment) grounded in supervenience, coarse-graining, and multiple realisability. The major theories of consciousness are positioned within this hierarchy according to which level they take to be critical, and for each level we develop operationalisable indicators and assess current AI systems against them. A
Bayesian model then combines theoretical credences with indicator evidence into an overall credence in a system's capacity for consciousness. In illustrative assessments, the verdict for current LLMs is driven as much by where theoretical credence is placed as by how the evidence is read: under different stipulated readings and credence distributions, assessments range from below 0.01 to roughly 0.8, showing sensitivity to assumptions. Finally, the consciousness indicators at each level closely overlap with the architectural features needed for general intelligence, suggesting that increasingly capable AI may become a stronger candidate for consciousness. The framework supports a structured agnosticism, in which theoretical commitments are made explicit, credences are updated as evidence accumulates, and assessments take the form of aggregated probabilities rather than verdicts.
Read the full abstract ▾
All authors Shamil Chandaria, Arvo Muñoz Morán, Fernando Rosas, Anil Seth, Henry Shevlin, Marcus Hutter, Thore Graepel, Adam Bales, Iulia Comsa, Murray Shanahan, Ruben Laukkonen, Morten Kringelbach, Chris Frith, Shane Legg
Computer Vision
EvolvingAvatar: Interactive 3D Head Generation That Adapts as Conversations Unfold
Junjie Chen, Fei Wang, Kun Li et al. (+5 more)
Interactive 3D head generation requires coordinated speaking and listening motion that responds to an evolving conversation. Existing generators use incoming observations as context but keep their parameters fixed, leaving conversational patterns unused as a learning signal. We introduce EvolvingAvatar, a causal generator that uses test-time training to adapt to user face
video and dyadic audio during interaction. Its dyadic context prediction objective provides a self-supervised learning signal from audiovisual context without target motion labels at test time. Persistent fast weights accumulate these updates within each conversation to guide motion generation, while transient jaw adaptation responds to current audiovisual context. Predicted
speech activity controls how persistent adaptation guides motion. We also introduce InterHead-Bench, a unified 455.95-hour
benchmark built from single-view and dual-view conversation
videos. Experiments show improved conversational motion statistics over strong baselines. On the hardest out-of-distribution split, generation improves as conversations unfold, reducing mismatch with recorded user-avatar expression statistics by up to 11.1% from the first interval.
Read the full abstract ▾
All authors Junjie Chen, Fei Wang, Kun Li, Yiqi Nie, Xun Yang, Yanbin Hao, Linfeng Zhang, Meng Wang
Machine Learning
Behavioral Foundation Models for Quality Diversity
Nazim Bendib, Nicolas Perrin-Gilbert and Olivier Sigaud
Behavioral Foundation Models (BFMs) are an emerging paradigm in reinforcement learning, playing a role analogous to large
language models in natural
language processing: they have shown remarkable versatility, enabling zero-shot performance, fast imitation, and online adaptation, all by exploiting the structure of a latent space. In this work, we investigate whether the latent behavioral space induced by BFMs can serve as an effective search space to discover large repertoires of behaviorally diverse and high-performing policies through Quality-Diversity (QD) methods. While QD methods generally search directly in high-dimensional policy parameter space, in this paper, we present BFM-QD, a framework that performs QD search in the compact latent space of a BFM. We further show that the BFM-QD framework provides a closed-form, gradient-free policy improvement operator that approximates a policy gradient update, but requires no critic training and no backpropagation. Across continuous-control
benchmarks spanning dense locomotion, sparse
navigation, and contact-rich manipulation, BFM-QD consistently outperforms parameter-space baselines, with particularly stark gains in sparse and deceptive settings, where all tested parameter-space QD methods collapse to near-zero performance. These results show the effectiveness of the BFM-QD framework, benefiting from the synergy between dimensionality reduction of the search space and offline pretraining from diverse behavioral data. This positions BFMs as a general-purpose backbone for QD optimization, extending their utility beyond zero-shot task solving to the discovery of diverse behavioral repertoires.
Read the full abstract ▾
Machine Learning
EvE: An Alternate Optimizer to Adam
Shashank Raj and Kalyanmoy Deb
Adam and its variants dominate neural network training, but a single run only reveals whether a configuration works well after most of its budget is spent, a poor fit for hyperparameter or architecture search, where configurations must be ranked cheaply and pruned early. We introduce EvE (Evolutionary Explorer), a steady-state, population-of-four differential
evolution (DE) optimizer with a targeted Adam fallback: each iteration proposes one candidate via DE, running a short burst of gradient descent only if the DE step fails to improve on the incumbent. Selection is greedy, so on a deterministic objective the best-so-far value is provably monotone non-increasing, and since gradients are used only as a targeted rescue, per-iteration cost stays within a constant factor of a single Adam step regardless of dimension. Under a fixed, evaluation-cost-matched budget, EvE wins or ties Adam on 76% of 70 (problem, dimension)
cells across seven scalable
benchmarks up to one million variables. On three real neural-network tasks (an MLP on MNIST, and LoRA fine-tuning of a 1.5B-parameter
language model on two
datasets) EvE finishes the same charged budget 1.7-3.9x faster, at a modest cost in final quality (about one accuracy point on MNIST, 9-11% higher relative test loss on the two fine-tuning tasks; on GSM8K, Adam is about 5 accuracy points more accurate, and fine-tuning lowers accuracy below the base model for both). Inside successive halving on UCI Adult, EvE completes hyperparameter and architecture searches 3.1-3.5x faster, ranking configurations about as consistently with Adam as Adam does with itself across seeds (Kendall's tau 0.66-0.69). EvE is not a total replacement for Adam as a final-stage trainer, but a fast, gradient-aware proxy for the search-heavy, budget-constrained regime one level up.
Read the full abstract ▾
Sound
Multimodal Target Speaker Extraction: Towards Unified Speaker Cues Across Modalities
Xinyuan Qian, Yanghao Zhou, Ziyang Jiang et al. (+10 more)
Target Speaker Extraction (TSE) is pivotal in
speech communication and human-computer interaction, enabling the isolation of a specific speaker's voice from complex acoustic environments, i.e., the cocktail party scenario. Although traditional TSE systems conditioned on enrollment
speech have progressed substantially, enrollment
speech as a cue has inherent limitations. Its reliability degrades when the target and interfering speakers have similar voice characteristics, when intra-speaker variability (e.g. changes in
emotion or speaking style) creates a mismatch between the enrollment and target
speech, or when the enrollment itself is contaminated by noise or competing speakers. This review surveys deep-learning-based TSE from the perspective of auxiliary target cues drawn from multiple modalities. We organize existing methods according to five types of information used to isolate the target speaker: audio enrollment, visual, spatial, textual/semantic, and neural cues. We also trace the
evolution from discriminative
estimators to variational,
diffusion, flow, codec, and foundation-model-based systems and summarize representative
datasets and evaluation metrics. We review the benefits and limitations of different cues and discuss challenges involving synchronization, missing or unreliable observations, data scarcity,
privacy, computational cost, and real-time operation. Finally, we summarize future directions concerning adaptive cue fusion, instruction-driven extraction, realistic evaluation, and trustworthy deployment. By jointly reviewing cue design, model architecture, training objectives,
datasets, and evaluation metrics, this article provides an overview of the current landscape and open problems in
multimodal TSE.
Read the full abstract ▾
All authors Xinyuan Qian, Yanghao Zhou, Ziyang Jiang, Yu Chen, Xinjia Zhu, Xueyan Chen, Qiquan Zhang, Zexu Pan, Jiaying Wang, Xianghu Yue, Jiadong Wang, Björn Schuller, Haizhou Li
Computer Vision
Remote Sensing Sparse-View 3D Gaussian Splatting via Depth Image-Based Rendering
Jiaming Kang, Zhengxia Zou and Zhenwei Shi
Remote sensing novel view synthesis under sparse observations remains challenging due to insufficient
geometric constraints and limited cross-view supervision. Existing Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) methods are prone to overfitting and face challenges of depth ambiguities, missing cross-view information, and insufficient constraints in under-observed regions. To address these challenges, we propose DIBR-GS, a neural Gaussian Splatting framework that exploits Depth Image-Based Rendering (DIBR) to generate pseudo views for cross-view consistency supervision. Specifically, reliable
geometric initialization is constructed by aligning
monocular depth priors with sparse SfM reconstruction, and cross-view appearance priors are incorporated into neural Gaussian representations to enhance appearance modeling under sparse observations. Furthermore, we introduce a progressive DIBR-based pseudo-view supervision strategy to provide additional
geometric and appearance constraints, enabling more complete reconstruction of weakly observed regions. In addition, a height-constrained anchor growth strategy is designed to suppress unreasonable Gaussian expansion. Experiments demonstrate that the proposed method achieves superior performance over existing approaches when training with only 3 input views. Compared with the previous best-performing method, it improves PSNR by 6.83 dB, with relative gains of 14% in SSIM and 60% in LPIPS, while maintaining competitive computational efficiency. Our code is available at https://github.com/kanehub/DIBR-GS
Read the full abstract ▾
Computer Vision
On-Policy Self-Distillation for Multi-Turn Image Editing
Liangbing Zhao, Le Zhuo and Mohamed Elhoseiny
Instruction-based image editing has achieved strong performance in single-turn settings, yet practical editing is often iterative, with each instruction applied to the output of the previous turn. We find that existing editing models degrade rapidly under recursive editing and attribute this failure to a train-test mismatch in the conditioning distribution: models are trained on clean source images but must repeatedly condition on their own imperfect outputs at inference time. To address this, we propose MT-OPSD, an on-policy self-
distillation framework that trains the model on self-generated conditioning states with editing supervision from a clean-conditioned teacher, without requiring multi-turn annotations. We further introduce LME-Bench, a
benchmark of 100 ten-turn editing sessions for evaluating long-horizon robustness. Experiments across three editing backbones show that MT-OPSD substantially improves long-horizon editing success and reduces multi-turn collapse while largely preserving single-turn editing quality.
Read the full abstract ▾
Machine Learning
Twist, Don't Tilt: Trajectory-Exact Constrained Decoding for Masked Diffusion Models
Aditya Thimmaiah, Lara Marinov, Jayanth Srinivasa et al. (+3 more)
Constrained decoding for Masked
Diffusion Language Models (MDLMs) aims to ensure that generated outputs satisfy a specified structure or syntax constraint. MDLMs generate outputs by repeatedly unmasking masked positions present in their current state. Recent strategies for constrained decoding constrain the model's per-step mean-field posterior (which factorizes over masked positions) by enforcing the desired constraint with an automaton. The resulting chain-structured factor graph allows exact constrained sampling via dynamic programming. However, despite each draw being exact and constraint-satisfying, we prove that their composition, in general, tilts away from the model's relative probabilities over valid trajectories, thus leading to trajectory bias. We derive an exact expression for this bias as a product of ratios measuring how valid continuation mass changes when the denoiser is reconditioned, and characterize when the bias vanishes. We then correct the bias by introducing TWISTER, the first automaton-twisted Sequential Monte Carlo decoder for MDLMs, using the step-exact decoder as the proposal. We show that for regular
language constraints, the Feynman-Kac correction is exactly computable, with the twists obtained efficiently using quantities pre-computed for step-exact sampling. We prove that the resulting Feynman-Kac model targets the unbiased Doob h-transformed path law conditioned on constraint satisfaction.
Read the full abstract ▾
All authors Aditya Thimmaiah, Lara Marinov, Jayanth Srinivasa, Haris Vikalo, Junyi Jessy Li, Milos Gligoric
Computer Vision
Simultaneous Translation between Sign Languages
Zetian Wu, Bowen Xie, Stefan Lee et al. (+1 more)
Deaf and hard-of-hearing (DHH) signers cannot converse in real time across different sign
languages today: existing sign-to-sign translation systems run offline, requiring the full source clip before any target sign is emitted. Live use cases - e.g. broadcast interpretation and two-way
video calls - instead demand simultaneous output, while the source signer is still signing. We present, to our knowledge, the first simultaneous sign-to-sign (S2S) translation system, with two wait-k regimes: test-time wait-k inference applied directly to a full-sentence model, and a trained wait-k model via
stochastic multi-path supervision. We further introduce ca-Stream-AL, a computation-aware latency metric for streaming output. Averaged across six S2S directions on both a smaller human-verified test set and a larger synthetic S2S corpus, our streaming system achieves a 38% ca-Stream-AL reduction while staying within a 9% DTW-PA-MPJPE increase and a 2.1 BLEU-4 drop compared to the full-sentence baseline. A word-order case study probes how the streaming model handles word order mismatch between different sign
languages - a consequence of simultaneous translation.
Read the full abstract ▾
All authors Zetian Wu, Bowen Xie, Stefan Lee, Liang Huang
Artificial Intelligence
TCSAlgBench: Benchmarking Automated Proving for Research-Level Theoretical Computer Science
Chutong Yang, Xiyuan Zhang, Yu Huang et al. (+7 more)
Large
language models perform strongly on competition mathematics, but their research-level
reasoning remains difficult to evaluate systematically. Theoretical computer science (TCS) connects
algorithm design to explicit guarantees and fundamental limits, providing a setting for evaluating whether models can justify computational improvements with arguments humans can inspect. We introduce TCSAlgBench, a
benchmark and reusable pipeline for natural-
language proof discovery, comprising 398
theorem-level challenges from 138 STOC and COLT 2026 papers. Expert-designed rules complete paper-specific context, preserve computational assumptions and quantitative guarantees, and withhold constructions when discovering an
algorithm is part of the task. For each task, prover systems receive
theorem statements and access to cited prior work. The pipeline supports fresh, versioned challenge batches from newly released papers. We evaluate ten model configurations from four families under direct inference and prover-verifier discussion, and compare four
agent workflows under matched model-call opportunities. All evaluations use the full
benchmark. In the model comparison, GPT-5.6 Sol max achieves the highest five-run verifier-accepted coverage at 23.6% after 10-round discussion. Discussion and repeated sampling improve coverage. In the separate
agent comparison using GPT-5.5 xhigh, decomposition improves coverage over discussion, and agentic planning achieves the highest five-run verifier-accepted coverage at 25.4%. TCSAlgBench provides a refreshable testbed for measuring progress in model
reasoning and studying how
agent workflows support research-level proof discovery.
Read the full abstract ▾
All authors Chutong Yang, Xiyuan Zhang, Yu Huang, Boran Han, Soonho Kong, Shuai Zhang, Vihang Prakash Patil, Zhen Han, Michael Bohlke-Schneider, Bernie Wang
Machine Learning
Control-Geometry Straightening for Sampling-Based Latent Planning
Ziang Fu and Ning Ning
Joint-
embedding predictive architectures enable planning with latent world models, but accurate transition prediction alone does not ensure that the planning objective is easy to optimize. We introduce Control-Geometry Straightening (CGS), a single auxiliary loss that learns planner-friendly representations by directly straightening control geometry for sampling-efficient planning. CGS matches pairwise cosine similarities among actions to those among corresponding latent differences only using local transitions from pixel-action pairs. The loss can be applied across world-model architectures using end-to-end learned or pretrained representations. Under linear-dynamics, our theoretical analysis connects this objective to temporal straightening and more balanced terminal-cost
curvature across the full planning horizon, yielding finite-budget guarantees for MPPI, local contraction results for CEM, and convergence bounds for gradient descent. Across four control environments and multiple planners, CGS improves planning with fewer sampled candidates and refinement steps, achieving success-rate gains up to 20 and 12.6 percentage points over LeWorldModel (LeWM) and its temporal-straightening variant (LeWM+TS), respectively, with sampling-based planners using 128 candidates per update. Probes, comparisons with DINO-WM architecture, and planner-side ablations clarify how latent motion organization, state dependence, and dynamical context shape planning behavior. Straightening control geometry thus makes good action sequences easier to find under limited planning budgets.
Read the full abstract ▾
Information Theory · Cross-listed from quant-ph
Low-Weight Canonical Logical Bases from Pair-Partition Codes
Koki Okada and Kenta Kasai
We construct complete canonical logical bases for
qubit CSS codes by assigning quaternary coefficients to binary circulant permutation
matrix pair-partition (CPM-PP) checks, constructing and normalizing logical representatives, and expanding the result into binary
matrices. When the two check systems have invertible submatrices on disjoint column sets, cofactor representatives are canonically paired by the inverse of a single pairing
polynomial. The resulting pairs span the entire logical space. When the pairing
polynomial is a cyclic-shift monomial with coefficient one, normalization preserves the binary weights of the representatives. We state the construction for general block dimensions and CPM size, work through a corresponding example, and report the parameters, check ranks, and basis weights of seven binary codes. Representative examples have parameters $[[320,80,14]]$, $[[448,112,18]]$, and $[[2048,512,24]]$. All three have maximum check weight 10 on both the X and Z sides. Their canonical logical representatives have binary weights 25, 27, and 27, respectively, on both the X and Z sides.
Read the full abstract ▾
Artificial Intelligence
Signatures of semantic search in the activations of large language models
Luke Leckie, Peter M. Todd and Jacob G. Foster
When recalling lists of concepts (e.g., animals) during the semantic fluency task (SFT), both humans and large
language models (LLMs) organise their output into clusters of related items (e.g., sea animals) that are punctuated by strategic switches between clusters. In humans, this pattern can be explained by a semantic foraging process, whereby distinct neural and behavioural signatures accompany within-cluster production ("exploit") and between-cluster switching ("explore"). Whether LLMs likewise represent these two search regimes within their internal states is unknown. Here, we apply a range of mechanistic interpretability techniques to provide evidence for this. In Study 1, we use the Jacobian lens (J-lens), which maps intermediate-layer residual-stream representations to
token-level activations, to show that concept-level activations predict switching. First, we find that switching coincides with low next-
token activations. Moreover, the probability of switching rises as the set of strongest J-lens activations (the J-space) becomes depleted of items from the category currently being produced, analogous to explore-exploit decision-making during patch foraging. We then show that middle-layer J-lens activations of abstract category-related labels (e.g., "water") increase in anticipation of switching into that category. We confirm these representations to causally influence switching by deriving steering vectors that target category switching. In Study 2, we identify generic residual stream directions that are activated during and in anticipation of switching. By steering activations along these directions, we bias increased or decreased rates of switching. Our study extends the semantic foraging framework to artificial intelligences and provides evidence that LLMs maintain distinct representational signatures for exploration and exploitation as they verbalise conceptual information.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Learning Conditional Expectation Operators via Functional Newton Updates
Thiago Ramos, Alek Fröhlich, Daniel Perazzo et al. (+1 more)
We introduce the Functional Spectral-Newton Method (FSNM) for learning the leading singular structure of a conditional expectation operator without fixing a basis or reproducing kernel
Hilbert space. FSNM fits a low-rank representation of the centered joint-to-product density ratio kernel by alternating functional Newton updates. Each update reduces to a preconditioned regression, which we approximate with vector-valued regression trees in a stagewise boosting procedure. At the population level, we establish descent and an $O(1/T)$ best-iterate block-stationarity rate under a relative weak-learner accuracy condition, and show that every nondegenerate local minimum over the full centered $L^2$ spaces is a globally optimal rank-$d$ approximation. Synthetic experiments show that FSNM recovers a low-rank density ratio and its leading spectral structure, and that the same learned kernel can answer multiple conditional queries without refitting.
Read the full abstract ▾
All authors Thiago Ramos, Alek Fröhlich, Daniel Perazzo, Massimiliano Pontil