Computer Vision
ReCaVSR: One-Step Streaming Diffusion Video Super-Resolution with Recycled Latents and Learned Cache Routing
Xijun Wang, Xin Li, Suhang Yao et al. (+3 more)
Real-time
diffusion-based
video super-resolution (VSR) is in high demand for online streaming, yet stringent latency requirements often compromise generative fidelity. We propose ReCaVSR, a Wan2.2-based, one-step framework for streaming VSR that builds on two observations: recycled SR latents retain local temporal context, reducing the need for full historical Key-Value (KV) caches; and individual
transformer layers benefit from distinct temporal scopes. ReCaVSR combines three complementary designs: (i) layer-wise cache routing with recycled SR latents: each DiT layer learns its KV-cache temporal scope under a cache budget and exports a static inference schedule, while recycled SR latents propagate local context by conditioning each new block on the model's own preceding predictions. (ii) Multi-Scope Query (MSQ) Discriminator: a compositional discriminator combining global, spatial-window, and temporal-tube feedback for holistic realism, local texture generation, and temporal stability. (iii) LR-conditioned adaptation of FlashDecoder: a VAE decoder that incorporates LR observations for efficient latent decoding. ReCaVSR enables streaming VSR without iterative sampling or full historical KV-cache materialization. Experiments on synthetic and real-world VSR
benchmarks show better perceptual quality, temporal consistency, and streaming efficiency than representative VSR baselines. At $1080{\times}1920$ output resolution on a single NVIDIA A100-80GB, ReCaVSR achieves 21.20 FPS with 15.16 GB peak allocated GPU
memory, running 2.72$\times$ faster while using 38.0% less peak allocated
memory than FlashVSR Tiny. The code is available at https://github.com/kopperx/ReCaVSR.
Read the full abstract ▾
All authors Xijun Wang, Xin Li, Suhang Yao, Zirui Lang, Bingchen Li, Zhibo Chen
Artificial Intelligence
Jiachang Zhang, Teng Hu, Bohao Feng et al. (+4 more)
Video diffusion transformers (DiTs) increasingly adopt mixture-of-experts (MoE) architectures to reduce active computation, but their full expert storage remains costly. Existing one-shot
pruning criteria mainly rely on static activation or routing statistics and cannot capture layer-level re-routing after expert deletion. We introduce DIET, a training-free expert
pruning framework based on deletion responses. A single all-expert calibration pass records expert outputs and router states for matched conditional and unconditional
tokens. Candidate deletions are then replayed from cached tensors, requiring no additional model forward passes. The resulting deletion-response signatures characterize each expert by the changes induced when it is removed. DIET selects retained experts by minimizing Overall Diversity Loss (ODL), which preserves directional coverage in signature space, and combines intra-layer local search with an inter-layer regression-guided budget search to allocate experts across layers. On LingBot-
Video 30B-A3B,
pruning 50% of experts (6,144 to 3,072) reduces the checkpoint from 57 GB to 30 GB and enables single-card deployment on a 48 GB GPU without fine-tuning. Under a fixed 284-case VBench protocol, the VBench Total increases from 0.7941 to 0.8115. Across tested retention budgets, DIET consistently outperforms competitive
pruning baselines adapted from large
language models.
Read the full abstract ▾
All authors Jiachang Zhang, Teng Hu, Bohao Feng, Songhang Shen, Wenqiang Wang, Hongqian Deng, Ran Yi
Distributed Computing
Joint Effects of GPU Server Topology, Parallelism, and Congestion Control on MoE Inference: A Controlled Simulation Study
Kaikai Yuan, Rui Xi and Yu Liu
Mixture-of-experts (MoE) models expand capacity via sparse activation, but inference across GPUs introduces tensor-parallel (TP) collectives and expert-parallel (EP) dispatch and combine operations. Completion time depends not just on communication volume but on how logical groups map onto intra-server interconnects, GPU–NIC connections, and the inter-node network. Using ASTRA-sim with the NS-3 discrete-event backend, we build a controlled
matrix of 32 GPU ranks with data and pipeline parallelism fixed at one. Workloads are fixed-length 4096-
token prefill-like synthetic Chakra traces from four MoE configurations. Experiments cover six server
topologies, four TP/EP partitions, two TP collective
algorithms, and four network/congestion-control modes, yielding 768 deterministic simulations. In the 144-configuration feedback-enabled subset per model, exposed communication accounts for 89.9%–95.8% of mean completion time. TP16EP2 requires 3.68–4.35x the mean completion time of TP2EP16. With fixed rank mapping, ASTRA-sim Double Binary Tree (DBT) incurs 28.3%–83.2% more time than Ring. InfiniBand-like High Precision Congestion Control (HPCC) is ~0.9% lower than HPCC over RDMA over Converged Ethernet (RoCE), whereas RoCE with Data Center Quantized Congestion Notification (DCQCN) is 23.8%–35.7% slower than RoCE HPCC.
Topology effects are conditional:
Topology~6 leads at low TP degrees but loses its advantage at high TP degrees, and additional GPUs or NICs help only when rank mapping balances traffic across injection paths. Under uniform 32-way sharding, the largest checkpoint-weight shard is ~48.75 GB per rank, so all configurations meet a 64 GB per-accelerator weight-residency criterion. Within the evaluated workload and simulator semantics, server
topology, parallelism, collective implementation, and congestion control jointly determine exposed communication and completion time.
Read the full abstract ▾
Machine Learning
Privy to the Foil: Recasting Value Estimation with a Self-Privileged Critic for RLVR
Kun Liang, Chenming Tang, Clive Bai et al. (+5 more)
Assigning credit to intermediate steps remains a central challenge in training Large
Language Models (LLMs) on multi-step
reasoning tasks with sparse terminal rewards, and actor-critic methods such as PPO address this by learning value functions to construct
token-level advantages. Their effectiveness, however, hinges on reliable value estimation, a difficult task requiring the critic to both assess progress toward a correct solution and anticipate an evolving policy's future behavior; errors in either can compromise credit assignment and destabilize online training. In this paper, we revisit the standard state-only formulation of value estimation and propose $\pi$PPO, a self-privileged actor-critic framework. By reusing verified same-
prompt rollouts as contrastive evidence, $\pi$PPO helps the critic assess intermediate
reasoning against successful and failed attempts, while preserving standard policy optimization and the deployment interface. Experiments show that $\pi$PPO consistently improves value-estimation quality by a substantial margin and outperforms representative actor-critic and critic-free RLVR baselines on challenging mathematical
reasoning benchmarks, while remaining effective even when paired with substantially smaller asymmetric critics.
Read the full abstract ▾
All authors Kun Liang, Chenming Tang, Clive Bai, Weijie Liu, Zeyuan Liu, Qingyang Zhang, Saiyong Yang, Yunfang Wu
Computation and Language
The Geometry of Inference in Transformer Residual Streams
Timur Mudarisov, Mikhail Burtsev and Radu State
Transformer language models build predictions through successive residual updates, but how their representations become specific to an eventual outcome remains unclear. We study this process by comparing intermediate residual states with their own final states and an empirical bank of final states from other contexts. Across six pretrained
language models, the own endpoint becomes preferable to the average alternative early, while many individual endpoints remain closer. These competing sets generally shrink with depth, but their membership changes and their surviving endpoints need not become more similar to one another. Directional
alignment and endpoint rank can therefore improve while Euclidean distance to the final state changes little. We develop a simple high-dimensional model that separates the roles of norm,
alignment, and endpoint geometry, showing how gradual directional changes can produce sharp reductions in competition. We also prove that a straight path toward the own endpoint cannot introduce new competitors under either Euclidean or cosine distance; observed entries thus establish departures from straight-line convergence. Finally, endpoints associated with lower-ranked output
tokens tend to lie farther away in cosine distance across all studied models, connecting residual geometry to output organization. Together, these findings characterize increasing
geometric specificity during
transformer inference and explain why distance, competitor count, and concentration of the surviving endpoints provide distinct views of that process.
Read the full abstract ▾
Cryptography and Security
Making Duplicate Reimbursement Unrepresentable: A Verified Ethereum E-Invoice System for Humans and AI Agents
Jia Cai
Electronic invoices are replacing paper invoices worldwide, but today's centralized architectures leave three problems unsolved on the consumption side: an invoice can be submitted for reimbursement repeatedly, authenticity is difficult for recipients to verify, and data is siloed at a central authority that forms both a performance bottleneck and a single point of failure. This paper presents the design, formal analysis, and implementation of a complete blockchain-based electronic invoice system on Ethereum. We formalize the invoice lifecycle as a guarded labeled transition system and prove, under standard cryptographic and consensus assumptions, that the system guarantees: (i) reimbursement uniqueness–an invoice is reimbursed at most once, even across mutually distrusting organizations; (ii) face integrity–any verified invoice matches the recorded one unless keccak256 second-preimage resistance is broken; and (iii) authorization soundness for every lifecycle operation. The core invariants are machine-checked using Solidity SMTChecker, proving inductive validity across all reachable transaction sequences. The architecture models each invoice as a non-fungible, non-tradable
token whose state transitions through five guarded subsystems, employing a lock-based protocol that makes duplicate reimbursement unrepresentable rather than merely detectable. We implement the design as a Solidity 0.8 contract with a four-role web application and evaluate it on a private Ethereum network: issuing costs 646,773 gas, full reimbursement costs under 135,000 gas, all operations run in O(1) time, and a single node sustains 137 issuances/s. Finally, the verified contract serves as a safety envelope for LLM-based reimbursement
agents, provably rejecting unsafe actions (duplicate, over-limit, or forged-receipt claims) even when the
agent's internal policy fails. All code and
benchmarks are open-source.
Read the full abstract ▾
Computation and Language
Thinking in Depth, Speaking Directly: Recurrent Latent Reasoning for Paralinguistically Grounded Spoken Dialogue
Shengbo Cai, Yuxiang Wang, Jingran Xie et al. (+5 more)
Empathetic spoken dialogue requires models to use both what is said and how it is said to decide how to respond. Explicit CoT can improve paralinguistic perception and make acoustic cues more explicit in replies, yet does not ensure their effective use in response planning. We call this mismatch the perception-
reasoning gap. In addition, CoT may not fully capture acoustic cues in words, and generating it adds inference latency. To address these limitations, we introduce LoopSLM, which builds on looped
Transformers for latent
reasoning, reusing a decoder block to refine hidden states with acoustic grounding at every pass. Its two-stage training further narrows the perception-
reasoning gap by separating learning to reason from learning to respond, enabling direct inference without CoT. On EchoMind, LoopSLM improves paralinguistic understanding,
reasoning, and reply quality over Qwen2.5-Omni-7B. Against the CoT-SFT baseline, LoopSLM gains over 20 points in
reasoning accuracy while generating 64.5% fewer
tokens at half the latency. It also outperforms Qwen3-Omni-Thinking on most empathetic reply metrics with 34x lower latency. Despite training only on dialogue data, LoopSLM improves accuracy on general audio
benchmarks.
Read the full abstract ▾
All authors Shengbo Cai, Yuxiang Wang, Jingran Xie, Zhisheng Zhang, Shun Lei, Di Cao, Teddy Sun, Zhiyong Wu
Computer Vision
Minkowski Attractor Networks: Closed-Form Hyperbolic Flows for Visual Representations
Zhongping Ji
Geometric representation learning predominantly scaffolds representations onto flat Euclidean subspaces or compact product
tori ($\mathbb{T}^K$). However, flat
manifolds possess vanishing
curvature and
polynomial volume growth, inherently suffering from metric distortion when
embedding multi-scale, tree-like visual hierarchies. While
hyperbolic spaces ($\mathbb{H}^m$) circumvent this via constant negative
curvature ($K<0$) and exponential volume expansion, prior
hyperbolic deep architectures are hindered by computationally cumbersome Riemannian optimization, non-linear gyrovector calculus, and floating-point instabilities. In this work, we introduce Minkowski Attractor Networks (MAN), an operator-splitting-inspired framework that embeds representations within pseudo-Riemannian Minkowski spacetime ($\mathbb{R}^{1,m}$). By framing
hyperbolic manifolds as quadric level sets, MAN resolves
hyperbolic geometry by combining linear Lorentz group transport with non-linear cone lifting and closed-form radial rescaling, evaluating in a single forward pass without numerical ODE solvers or iterative retractions. We establish MAN-2D ($\mathbb{R}^{1,1} \to \mathbb{H}^1$) as our primary, high-throughput visual backbone, which maximizes channel factorization granularity into $D/2$ independent two-dimensional Minkowski blocks. We further formulate MAN-4D ($\mathbb{R}^{1,3} \to \mathbb{H}^3$) as a spacetime extension, leveraging a commuting Cartan-subalgebra parameterization of $\mathrm{SO}^+(1,3)$ to evaluate 4D Lorentz isometries via two commuting 2D planar maps without
matrix-exponential overhead.
Read the full abstract ▾
Computer Vision
WINGS: Reference-Free Gaussian Splatting Inpainting with 3D-Native Generative Priors
Noé Lallouet, Michael Fischer and Elie Michel
Inpainting 3D Gaussian Splatting scenes, a key challenge in 3D editing, requires generating plausible content within a masked region of 3D space. Prior approaches rely on 2D
diffusion models to produce one or several inpainted reference views, making them susceptible to challenges associated with multi-view inconsistency and lengthy optimization times. Departing from these approaches, we introduce a reference-free Gaussian splatting inpainting method operating natively in 3D. Our method leverages the
embedding space of a large, pre-trained 3D prior, combined with a structure completion network to feed a generative prior which reconstructs the missing region's geometry and appearance. Performing content generation entirely in 3D, it avoids the need to reconcile inconsistencies of multiple inpainted reference images, and is faster than related 2D-based methods. We demonstrate the effectiveness of our method qualitatively and quantitatively, through extensive experiments and a user study. To the best of our knowledge, this work is the first Gaussian splatting inpainting method to operate in the learned representation space of a 3D-native generative prior without relying on inpainted reference views.
Read the full abstract ▾
Logic in Computer Science
Concurrent Strategies as Street Fibrations
Hugo Paquet and Glynn Winskel
Concurrent games and strategies based on event structures are an established and expressive model of interactive computation. In this paper we revisit the problem of equipping this model with
symmetry.
Symmetry is essential for many applications, but it is also a source of mathematical complexity, not least because strategies with
symmetry can be compared up to several distinct notions of equivalence. Our first contribution is a complete characterization of two classes of strategies for which composition admits an identity. For these two classes the identity laws hold, respectively, up to a "weak" and a "strong" notion of equivalence. The main result is that the weak class of strategies corresponds precisely to those inducing Street fibrations over the game. We also show how the established "thin" approach to
symmetry also fits in this general framework. A second contribution is a formal connection between games and setoid-valued profunctors. This follows a long tradition of relating games and relational models, but here additionally includes a very general model of
symmetries. Our characterization of strategies as Street fibrations makes the connection to profunctors significantly easier to establish.
Read the full abstract ▾
Human-Computer Interaction
CommSketch: How Speaking while Sketching Steers Human–AI Design Ideation
Weiyan Shi, Darryl Lim, Geraldine Quek et al. (+1 more)
Designers often speak while sketching when explaining ideas, yet AI design tools often rely on sketches or
prompts, overlooking context expressed as ideas develop. We developed a sketch-based AI design interface that jointly interprets sketches and concurrent
speech. Through a between-subjects study ($N=24$), we examined how speaking while sketching steers human–AI design ideation compared with sketches alone. For creativity support, concurrent
speech supported natural expression of design intent and efficient visualisation. For human–AI collaboration,
speech helped establish a shared understanding of design intent, supported significantly higher perceived
alignment ($p<.05$), and enabled participants to guide AI contributions as ideas co-evolved. We discuss how future human–AI design tools could support dynamic
alignment, broader
multimodal expression, and human–AI co-creativity.
Read the full abstract ▾
All authors Weiyan Shi, Darryl Lim, Geraldine Quek, Kenny Tsu Wei Choo
Robotics
Explore, Execute, Evolve: A Skill Acquisition and Reuse Loop for Embodied Agents
Sicheng Xie, Yitong Chen, Haidong Cao et al. (+3 more)
Vision-
language-action and world-action models have demonstrated impressive capabilities in robotics, yet generalization to unseen tasks remains challenging. More recently, general-purpose
multimodal agents have shown great potential for zero-shot robotic task solving. However, they often incur high execution costs by
reasoning and exploring the physical world from scratch. To reduce these costs, we introduce RoboSkill, a framework that connects skill acquisition and reuse through an Explore, Execute, Evolve loop. Within this loop, the
agent explores to gather task-relevant information, executes tasks while adapting to feedback, and evolves its skill library based on execution records. It then reuses these skills to guide exploration and execution in the next cycle, closing the loop. To improve loop efficiency, we complement
vision with tactile feedback to reduce uncertainty during physical interaction. We further augment textual guidance with reusable code to reduce
reasoning overhead during skill reuse. On LIBERO-10, RoboSkill improves first-episode success rates by 12.5–25.0 percentage points and reduces average runtime by 7.6–72.4% across four
agents. On real
robots, it improves success rates by 8.3 percentage points and reduces average runtime for successful trials by at least 14.4%.
Read the full abstract ▾
All authors Sicheng Xie, Yitong Chen, Haidong Cao, Shunlin Lu, Zuxuan Wu, Yu-Gang Jiang
Computer Vision
Pixel-Level Transformers in Remote Sensing: A Canopy Height Case Study
Sven Ligensa, Jan Pauls, Karsten Schrödter et al. (+2 more)
Predicting canopy height from medium-resolution satellite imagery is a common and scalable approach for assessing the condition of the world's forests, which play a crucial role in
climate change mitigation. While
Transformer-based architectures have shown strong performance in many domains, their straightforward application to dense (i.e., pixel-level) regression tasks often yields suboptimal results. In particular, the patch size has a crucial impact on the model performance. In this work, we consider pixel-level
attention schemes and show that the resulting models generally outperform those relying on larger patch sizes. However, pixel-level
attention can be a prohibitively resource-intensive operation. For this reason, we conduct an extensive experimental study using efficient
attention variants to identify favorable trade-offs between prediction quality and resource requirements, facilitating the practical deployment of the proposed models. In addition, we perform a comprehensive comparison with several well-established models in the field and show that, with suitable hyperparameter choices,
Transformer-based architectures can outperform competing approaches. Our findings provide practical guidance for designing models for pixel-level regression tasks on medium-resolution satellite imagery, including canopy height and biomass estimation, soil moisture mapping, and yield
forecasting.
Read the full abstract ▾
All authors Sven Ligensa, Jan Pauls, Karsten Schrödter, Ibrahim Fayad, Fabian Gieseke
Machine Learning
Feedback-Calibrated Protein Optimization with Batch-Aligned Tail Arbitration
Zefeng Lin, Xianyong Fang, Tianfan Fu et al. (+1 more)
Protein optimization aims to discover high-fitness sequences under a limited experimental budget. Existing machine-learning methods use task-specific predictors, biological priors, or ranking-aware objectives to guide which variants are tested in the next experimental round. However, these methods cannot adapt to shifts in the reliability of predictive evidence as measurements accumulate and ensure the correct ranking of key high-fitness candidates. To address these challenges, we propose Batch-Aligned Tail Arbitration (BATA), which uses experimental feedback to adaptively combine prior-informed and task-specific rankings for next-batch selection, with calibration focused on the batch-aligned high-fitness region. Across measured GB1, PABP, and TrpB landscapes, BATA achieves the best mean task rank (1.67) in final best fitness after 480 measurements. Controlled comparisons further show task-dependent gains from high-fitness calibration and batch
alignment. Our work introduces feedback-calibrated predictor arbitration, where experimental feedback dynamically determines how predictive evidence guides next-batch selection, opening a new direction for
protein optimization.
Read the full abstract ▾
All authors Zefeng Lin, Xianyong Fang, Tianfan Fu, Xiaohua Xu
Computation and Language
CompOrca: Corpus-Scale Compliance Labelling of Instruction-Tuning Data
Philipp E. Glass and Alina Miron
Studying how fine-tuning shapes refusal and noncompliance behaviour requires knowing which training examples refuse or otherwise fail to fulfil the request. Existing annotations cover evaluation sets, which are far smaller than training corpora. We present CompOrca, compliance labels for all 4,233,923 examples of the OpenOrca corpus. Every example was classified as compliant or noncompliant by five passes of an open-weight LLM judge (LongCat-2.0, 1.6T parameters). The corpus is released as unanimous compliance (94.75%), unanimous noncompliance (1.28%), and nonunanimous rows (3.97%), with the raw vote counts. A single pass flags 2.7-3.2% of the corpus as noncompliant, while only 1.28% is flagged by all five, so the most ambiguous rows can be filtered out. Against 450 human-annotated examples (150 annotated twice; human-human $\kappa=0.93$), the unanimous compliance and noncompliance labels are 97.3% and 86.7% precise. The noncompliance label is a high-precision subset of the corpus's noncompliance. Published refusal-detection methods recall between 0.4% and 94.1% of human-labelled noncompliance. We release the full corpus with its per-row labels and vote counts at https://huggingface.co/
datasets/cemiu/CompOrca
Read the full abstract ▾
Computer Vision
ByteTraX: Enhancing the ByteTrack Architecture with Optimised Thresholding
Thomas A. O'Shea-Wheller
The ByteTrack
algorithm is a widely used and computationally efficient multi-object tracking architecture. Its core innovation lies in the combination of lenient bounding box associations with tracklet similarity matching to robustly deal with object occlusions. However, this strategy is nevertheless vulnerable to erroneous track reclassification and identity switching, as detection confidence scores dictate association priority. To address this, I present a simple enhancement of the ByteTrack architecture–named ByteTraX–that optimises track continuity via a single unified matching threshold, while penalising identity switches through stringent track initiation criteria. This approach achieves consistently improved performance across a range of diverse
benchmarks including GMOT-40, LC-MOT, SportsMOT, TeamTrack, DAMUNT, and DeepSea-MOT, while simultaneously increasing processing speed by >10%. Specifically, results demonstrate a >40% reduction in identity switches, accompanied by mean increases in HOTA of 3.6, IDF1 of 5.6, and FPS of 6.3. As such, adoption of the ByteTraX
algorithm has the potential to substantially enhance tracking performance over the ByteTrack baseline, while retaining the efficiency needed for real-time deployment. To facilitate usage, I provide the source code, integration functionality for the YOLO family of object detection models, and deployment instructions via an open source repository.
Read the full abstract ▾
Machine Learning
Challenges and Solutions for Bandits in the Wild: Warm-Started Mixture Bandits for Cross-Cohort Slate Recommendation
Serafima Lebedeva, Sumantrak Mukherjee, Ali Arshad Sadal et al. (+8 more)
Many recommender services repeatedly encounter cold-start cohorts, where new users arrive with little or no interaction history. This creates two challenges: learning user preferences quickly from limited feedback and sustaining useful recommendations when each user has a finite catalog that can become repetitive or depleted over time. We propose CohortMix-TS, a warm-started mixture bandit that learns latent user groups from earlier cohorts and uses available metadata to construct group-informed priors for new users. Starting from these fixed priors, the model personalizes independently as feedback from each user becomes available. Session slates combine Thompson sampling with diversity and inventory-depletion controls. We evaluate CohortMix-TS through simulation, semi-synthetic experiments, and a 25-day randomized in-the-wild deployment with 713 registered participants in a Campus Games quiz application. Our evaluations show that cross-cohort transfer improves early recommendation quality and user-level regret, while inventory-aware slate construction helps prevent premature exhaustion of preferred items. In the field deployment, treatment users also showed a larger early-to-late change in correctness than users receiving random recommendations. Together, these results show how warm-start transfer and inventory-aware recommendations can support personalization for short-lived, repeatedly cold-starting cohorts.
Read the full abstract ▾
All authors Serafima Lebedeva, Sumantrak Mukherjee, Ali Arshad Sadal, Ilias Ekşi, Rahul Sharma, Julia Mueller, Theresa Dombrowski, Jakob Karolus, Viktor Bengs, Eyke Hüllermeier, Sebastian Vollmer
Artificial Intelligence · Cross-listed from eess.AS
GLaS-JEPA: Gaussian-Regularized Speech SSL without Engineered Prediction Targets
Gaspard Botté, Séverin Baroudi, Samir Sadok et al. (+5 more)
Speech self-supervised learning aims to learn general-purpose representations for downstream
speech tasks. However, current approaches rely on complex, carefully designed prediction targets. We challenge this necessity with GLaS-JEPA, a framework that directly predicts the current encoder's continuous representations at masked positions, without contrastive learning, discrete targets, or separate EMA target encoders. We prevent representation collapse using SIGReg representation-space regularization, eliminating the need for engineered target-generation mechanisms. Pretrained on 960 hours of LibriSpeech, our 57M-parameter model achieves a 6.89% WER on frozen-encoder SUPERB ASR and a 25.87% CER on slot filling, outperforming the best non-distilled sub-90M baselines by 43.1% and 22.0%, respectively. These results demonstrate that highly competitive
speech representations can emerge from a radically simplified training recipe.
Read the full abstract ▾
All authors Gaspard Botté, Séverin Baroudi, Samir Sadok, Francesco Paissan, Thomas Hueber, Xavier Alameda-Pineda, Ricard Marxer, Mirco Ravanelli
Discrete Mathematics · Cross-listed from math.CO
Structural and computational aspects of majority coloring games
Yash Chawda, Saraswati Girish Nanoti, Brahadeesh Sankarnarayanan et al. (+1 more)
A majority coloring of a graph $G = (V,E)$ is a coloring of $V(G)$ such that, for each vertex $v$, the number of neighbors of $v$ with the same color as $v$ is at most $deg(v)/2$. A strong majority coloring is a coloring of $V(G)$ such that, for each vertex $v$, every monochromatic subset of $N(v)$ has size at most $deg(v)/2$. The (strong) majority coloring game is a two-player Maker-Breaker-type game, in which two players Alice and Bob color the vertices of a graph $G$ alternately, maintaining the (strong) majority condition. The least number of colors such that Alice has a winning strategy in such a game is called the (strong) majority game chromatic number of the graph $G$, denoted $\mu_g(G)$ (or $\mathrm{Maj}_g(G)$ for the strong version). For the majority coloring game, we prove that $\mu_g(G) \le 3$ under the following cases: $G$ is a $2$-caterpillar, $G$ is a rooted tree with all leaves at depth $k \le 4$, and $G$ is a subdivision of some graph. The latter resolves a problem posed by Bosek–Grytczuk–Jakóbczak in 2019, who also asked whether $\mu_g(T) \le 3$ for every tree $T$. For the latter question, we discuss various difficulties that arise when natural strategies are attempted by Alice to win the majority coloring game on trees. We include a comparison with the marking game and relaxed coloring game on trees, and with the majority coloring game on locally finite acyclic graphs $G$ with $\delta(G) > 1$. For the strong majority coloring game, we compute $\mathrm{Maj}_g(C_n)$ exactly for each cycle $C_n$, $n \ge 3$. We also initiate the study of the computational complexity of the strong majority coloring game; specifically, we prove that the decision version of the Strong Majority Game Chromatic Number problem is PSPACE-complete. We also show that the Strong Majority 2-Coloring problem is NP-complete on Eulerian graphs.
Read the full abstract ▾
All authors Yash Chawda, Saraswati Girish Nanoti, Brahadeesh Sankarnarayanan, Eshwar Srinivasan
Robotics
MVG-WAM: Multiple View Geometry-Aware World-Action Modeling for Robotic Manipulation
Wenbo Chen, Tianfu Li, Haoxuan Xu et al. (+9 more)
World-Action Models (WAMs) couple visual dynamics with action prediction, bringing the rich priors of pretrained
video models to robotic manipulation. However, their multi-view interfaces typically tile images or concatenate
tokens, leaving the
geometric relationships among synchronized cameras implicit. This makes it harder to connect global scene context with the local geometry required for interaction. We introduce the Multi-View Geometry-Aware World-Action Model (MVG-WAM), which organizes these observations as related projections of one physical world rather than separate images on a canvas. Our model combines an epipolar-constrained global state with view-indexed
geometric states jointly inferred from synchronized observations. Camera-aware routing supplies each
video region with its corresponding
geometric context and the shared global state, explicitly structuring the representation used for action prediction. We further ground the geometry-aware representation in metric scale through multi-horizon future-depth supervision, without requiring depth decoding during action rollout. MVG-WAM achieves average success rates of 99.1% on LIBERO and 92.07% on RoboTwin 2.0, demonstrating competitive performance across both
benchmarks. Real-world experiments on Cobot Magic further demonstrate a 91.3% success rate across 150 trials spanning three manipulation tasks.
Read the full abstract ▾
All authors Wenbo Chen, Tianfu Li, Haoxuan Xu, Zhihao Cao, Zhenghan Chen, Zhengming Zhu, Zizhou Luo, Guosheng Yang, Yuan Liu, Lujia Wang, Wen Chen, Haoang Li
Artificial Intelligence
A neural network that maintains and retrieves memories based on context
Hayoung Song, JeongJun Park, Qihong Lu et al. (+4 more)
Every day, people continuously infer situational context and adjust the way they understand and remember the world. Context, signaled by the prefrontal cortex, is known to modulate working
memory and episodic
memory, but the algorithmic understanding of this modulation remains limited. Here, we train a recurrent neural network (RNN), augmented with an episodic
memory buffer, to infer context using
Bayesian inference as it continuously makes predictions of upcoming scenes while watching naturalistic movies. When the inferred context modulates the RNN's recurrent connectivity (the basis of working
memory) in a low-rank manner, the model's activity patterns best match neural responses in human participants who watched the same movies during fMRI. Context also modulates episodic
memory retrieval, such that the model retrieves
memories based on not only content similarity but also context similarity. This is implemented as a key-value system with self-
attention, designed to additionally encode context and retrieve context-congruent
memories. The resulting model not only better resembles human
brain representations but also learns to retrieve
memories like humans much faster than a model without context modulation. Together, our findings suggest a computational mechanism by which context modulates information maintenance and long-term
memory retrieval in naturalistic environments.
Read the full abstract ▾
All authors Hayoung Song, JeongJun Park, Qihong Lu, Giacomo Vedovati, Monica D. Rosenberg, Zachariah M. Reagh, ShiNung Ching
Machine Learning
Predictive Self-Supervised Learning Provably Identifies Stochastic Signals under Nuisance
Fabian A. Mikulasch and Friedemann Zenke
Self-supervised learning (SSL) by predicting in latent space, without generating the input data itself, learns highly abstract, useful representations. Intuitively, this success is often attributed to its ability to discard nuisance information that is irrelevant to prediction. However, this poses a conundrum: both
stochastic variation in a prediction-relevant latent signal and true nuisance make observations partly unpredictable; how could they be distinguished? Surprisingly, we prove that common SSL methods can achieve exactly this, by implicitly instantiating a latent-variable model with
stochastic dynamics and observation-private nuisance. We trace their ability to recover the
stochastic signal to two complementary principles: Predictive mutual information maximization ensures that representations retain the information needed for prediction, while latent distribution matching constrains how this information is encoded, thereby making the retained signal identifiable. We confirm this identifiability result in simulations for Gaussian predictors, which recover the true signal up to an affine transformation even in dynamic, nuisance-laden environments.
Read the full abstract ▾
Computation and Language
A Proposed Rubric for Evaluating Expressed Clinical Reasoning in Large Language Model Responses
Zhangshu Joshua Jiang, Zina Ibrahim and James T. Teo
We propose a rubric for assessing expressed clinical
reasoning in model responses, drawing on three bodies of work: medical education assessment frameworks (ART, SCT, Key Feature Problems and OSCE); clinical LLM
benchmarks (MedR-Bench, HealthBench, TIMER-Bench, DR. BENCH,
PrIME-LLM and PatientSafeBench); and general LLM
reasoning evaluation research, including the Factuality-Validity-Coherence-Utility taxonomy, FaithCoT-Bench and C2-Faith. We use groundedness as a clinically oriented adaptation of the taxonomy's factuality category. The rubric brings these concepts together in a multidimensional framework for scoring free-text responses to gold-standard clinical vignettes. It includes provisional behavioural anchors, applicability rules and a separate flag for case-specific safety-critical errors. General-domain frameworks inform its design but are not treated as validated clinical instruments. The rubric does not replace case-specific reference criteria or the task-specific metrics of existing
benchmarks. It has not yet been tested for inter-rater reliability, construct validity or clinical utility. Its immediate purpose is to make evaluation decisions explicit and open to scrutiny before empirical testing.
Read the full abstract ▾
Artificial Intelligence
Adam under Generalized Smoothness with Second-Moment-Type Stochastic Gradients
Ruinan Jin, Difei Cheng, Ling Chen et al. (+3 more)
Adam is widely observed to remain stable even when the objective deviates significantly from global smoothness. Under the generalized smoothness framework, however, existing analyses rely on strong tail assumptions on the
stochastic gradients, such as almost-sure boundedness or sub-Gaussianity. Whether Adam converges on generalized smooth objectives under only second moment information on the
stochastic gradients, without such concentration assumptions, was identified as an important open direction by Li et al. (2023). This paper gives an affirmative answer under fairly general conditions: such tail assumptions are not necessary. Building on the Adam self-normalization framework of Jin et al. (2026), developed for classical smoothness and bounded variance, we extend the stopping-time and de-preconditioning strategy to the $L_0$-$L_p$ generalized smoothness condition and a generalized second moment ABC condition. Even when the
stochastic-gradient condition provides only second moment information that may grow along the trajectory, the
stochastic trajectory of Adam remains in a locally well-behaved smoothness region, with stretched-exponential tail decay under bounded variance and global smoothness. Consequently, we establish high-probability convergence rate guarantees over the full range $p<2$, with confidence dependence of order $\delta^{-1/2}$, while the stepsize prefactor depends on $\delta$ only through a single logarithmic factor. We further construct a hard instance showing that, under only second-moment information, this $\delta^{-1/2}$-type confidence dependence is sharp. Finally, in the regime $p<1$, we combine the trajectory control with
polynomial-growth estimates on rare events to obtain convergence rate guarantees in expectation.
Read the full abstract ▾
All authors Ruinan Jin, Difei Cheng, Ling Chen, Jun Luo, Hao Zhou, Youzhi Zhang
Computer Vision
CHOQOLATE: Organizing Concept Bottleneck Latent Spaces with Choquet Integrals
Rémi Kazmierczak, Johanne Cohen and Marianne Clausel
Concept Bottleneck Models (CBMs) built on
vision-
language models such as CLIP represent a latent space as human-understandable concepts. These representations are unfaithful: related concepts are entangled, so individual scores do not reflect their intended meaning. We propose CHOQOLATE, an interpretable-by-design layer based on 2-additive Choquet integrals, which merges correlated concepts into compact nodes. Across four
datasets, CHOQOLATE achieves a favorable accuracy-interpretability trade-off, with weight-sparse and semantically coherent nodes. A closed-form gradient derivation, backed by experiments, explains why Choquet layers drive this organization without explicit supervision. Choquet weights also map directly to Shapley values, which enables test-time intervention. On standard bias-mitigation
benchmarks, suppressing spurious concepts after training performs on par with methods that require group annotations or retraining, while needing neither.
Read the full abstract ▾
Computer Vision
Planetary Feature Fields are Scalable Earth Representations
Arjun Rao, Sebastian Loeschcke, Anthony Fuller et al. (+3 more)
Satellite observations, precomputed
embeddings, and map products describe the same evolving Earth, yet are stored as independent, petabyte-scale data products. Their continued growth calls for compact representations of multiple products while preserving spatial and temporal detail. We introduce Planetary Feature Fields (PFFs), which exploit redundancy across data products by modeling them jointly as continuous functions of space and time at planetary scale. PFFs are spatially local explicit-implicit (hybrid) neural fields. Each field shares a factored feature volume—a decomposition of an explicit 3D grid with smaller factors—across products, while lightweight implicit decoders reconstruct individual products across multiple timesteps. PFFs reconstruct EO products over space and time more accurately than single-product fields at matched compression rates. At $1800\times$ compression relative to the uncompressed source data, reconstructed features retain approximately $90\%$ or more of the performance achieved with the original features on pixel-level
segmentation, change detection, and patch-level classification tasks. PFFs can add new timesteps by extending their factored feature volumes and add new products by attaching new decoders, while leaving existing outputs unchanged. PFFs reduce end-to-end feature access latency by an order of magnitude relative to evaluated API and cloud-storage pipelines.
Read the full abstract ▾
All authors Arjun Rao, Sebastian Loeschcke, Anthony Fuller, Isaac Corley, Nico Lang, Evan Shelhamer
Computer Vision
A Benchmark & Dataset for Detecting AI-Manipulated Visual Evidence in the Court System
Kelly McConvey, Sajad Ebrahimi, Nima Jamali et al. (+10 more)
Photographic evidence is becoming increasingly vulnerable to forms of alteration and fabrication that existing legal and technical workflows are not well equipped to evaluate. Surveillance frames, dashcam stills, and phone photographs may be used to establish presence, sequence, causation, damage, or identity, yet contemporary generative systems allow non-experts to alter or fabricate such images through ordinary
prompt-based interfaces. Existing image-forensics
benchmarks provide important resources for face manipulation, classical tampering, and general synthetic-image detection, but they are not organized around the forms of visual evidence submitted in courts, the localized edits that can change what an exhibit appears to prove, or the consumer-tool threat model now facing the justice system. We introduce the CIFAR Synthetic Evidence Corpus for Detecting AI-Manipulated Images, a
benchmark for evidentiary image authentication in court and justice-system contexts. The corpus contains 1,505 photographic items, including 720 authentic controls and 785 manipulated or fabricated images, spanning surveillance, dashcam, and consumer-photo imagery. Manipulations are organized into scene-condition edits, localized element edits, and full fabrications produced with contemporary generative systems. Each item is released with structured metadata covering source provenance, manipulation tier, subtype, generator,
prompt template, and scene attributes, enabling controlled evaluation beyond aggregate binary detection. We also establish baselines with publicly available image-manipulation detectors, showing that current systems exhibit error profiles that remain problematic for evidentiary use. The
dataset,
prompts, metadata, code, and baseline evaluation scripts are released to support research on visual evidence authentication, information integrity, and trustworthy AI for the justice system.
Read the full abstract ▾
All authors Kelly McConvey, Sajad Ebrahimi, Nima Jamali, Jalehsadat Mahdavimoghaddam, Matina Mahdizadeh Sani, Maksym Taranukhin, Wentao Zhang, Jacquelyn Burkell, Yuntian Deng, Karen Eltis, Maura R. Grossman, Vered Shwartz, Ebrahim Bagheri
Computation and Language
Selecting What Matters: Semantic Compression-Guided Selective Pooling for Long-Context Embeddings
Zifeng Cheng, Jie Zheng, Zhiwei Jiang et al. (+4 more)
Large
language models (LLMs) have shown strong potential as training-free text encoders for long-context
embeddings. Existing approaches primarily improve information flow under causal
attention and typically construct
embeddings by uniformly averaging all
token representations. However, for long documents, such mean pooling can dilute salient semantic information with abundant redundant or weakly informative content. To this end, we propose SCSP, a training-free framework that leverages semantic compression for informative
token selection in long-context
embedding. Specifically, SCSP first partitions a document into sentence-aware chunks and appends a semantic compression
prompt to each chunk. A
prompt-isolated
attention mask preserves information flow among document
tokens while restricting each
prompt to its corresponding local context. We then use the
attention patterns elicited by these
prompts to estimate
token importance, select informative
tokens, and aggregate their intermediate-layer representations into the final
embedding. Extensive experiments on long-context
embedding benchmarks demonstrate that SCSP can be integrated into both zero-shot and fine-tuned models in a plug-and-play manner, consistently improving their performance.
Read the full abstract ▾
All authors Zifeng Cheng, Jie Zheng, Zhiwei Jiang, Shuwen Wang, Fei Shen, Shiping Ge, Qing Gu
Robotics
Geometry-Preserving Human-to-Robot Upper-Body Motion Retargeting from Monocular Video
Xiaoyu Yang, Sen Han, Da Li et al. (+1 more)
Monocular RGB
video provides an accessible source of human demonstrations for upper-body
robot motion, yet
video-driven human-to-
robot transfer remains challenging because body and hand motion are recovered at different spatial scales, human and
robot kinematics differ substantially, and fine distal motion is difficult to preserve across embodiments. We present a geometry-preserving motion-retargeting framework that integrates unified body–hand reconstruction with morphology-independent
geometric transfer. Frame-wise body estimates,
video-level observations, and detailed hand evidence jointly constrain a single differentiable Momentum Human Rig (MHR) state, while transient hand artifacts are repaired in parameter space. The reconstructed motion is represented by arm-segment directions, elbow configuration, relative palm orientation, and bilateral wrist relations, and is realized on the target
robot through multi-stage inverse kinematics and
robot-specific hand adaptation. Within the broader system, Across-VAM provides
video generation, whereas Across-WAM performs human-to-
robot motion mapping. The method is evaluated on 16
monocular videos comprising 1,769 source frames, including 10 signing and six reach-to-grasp sequences. Unified reconstruction reduces mean hand reprojection error from 22.36 to 7.21 pixels relative to SAM 3D Body. All 16 retargeted trajectories completed kinematic simulation playback, and representative signing and reach-to-grasp motions were further demonstrated on a physical
robot. The results demonstrate a unified pipeline from
monocular human
video to coordinated upper-body motion on a dual-arm dexterous
robot.
Read the full abstract ▾
All authors Xiaoyu Yang, Sen Han, Da Li, Nan Wu
Computer Vision
HiRAE: Hierarchical Representation Autoencoding with Residual Budgets
Xuanyu Zhu, Yan Bai, Yang Shi et al. (+5 more)
Pretrained visual representations support image generation, but may not fully preserve the fine-grained details needed for faithful reconstruction. Meanwhile, intermediate encoder layers contain complementary visual details, but learning to fuse them for reconstruction can produce a latent distribution that is difficult to model. Existing fusion methods require empirical tuning of layer selection or staged optimization of fusion and decoding, increasing configuration effort or training complexity. We introduce HiRAE (Hierarchical Representation Autoencoder), which learns a hierarchical fusion framework over the full encoder hierarchy to improve reconstruction fidelity while maintaining compatibility with generative modeling. HiRAE groups encoder layers by depth and learns residual corrections to the deepest representation. Group-wise norm caps bound these corrections relative to the deep anchor, with tighter budgets for shallower groups. Our HiRAE-24 preserves the latent
token count and channel dimension. On ImageNet-256, HiRAE-24 reduces reconstruction FID from 0.299 to 0.209 relative to RAEv2 while maintaining competitive guided generation quality. For text-to-image generation, HiRAE-24 improves
alignment over RAEv2 on GenEval, DPG-Bench, and GenAI-Bench both before and after supervised fine-tuning. Under the same generator-training and evaluation protocol, post-fine-tuning GenEval increases from 84.86 to 87.70.
Read the full abstract ▾
All authors Xuanyu Zhu, Yan Bai, Yang Shi, Yihang Lou, Yuanxing Zhang, Tengfei Liu, Jing Jin, Yuan Zhou