# Research Papers — 2025-12 · bundle page 69 of 175

> Full-text markdown of papers #3401–3450 of 8703 published in 2025-12, newest first. AI-readable mirrors of the full 8703-paper 2025-12 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-12/page/69
[← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/68.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-12/page/70.md)

### VET Your Agent: Towards Host-Independent Autonomy via Verifiable Execution Traces

Authors: Artem Grigor, Christian Schroeder de Witt, Simon Birnbach, Ivan Martinovic
Published: 2025-12-17
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2512.15892v1

Recent advances in large language models (LLMs) have enabled a new generation of autonomous agents that operate over sustained periods and manage sensitive resources on behalf of users. Trusted for their ability to act without direct oversight, such agents are increasingly considered in high-stakes domains including financial management, dispute resolution, and governance. Yet in practice, agents execute on infrastructure controlled by a host, who can tamper with models, inputs, or outputs, undermining any meaningful notion of autonomy. We address this gap by introducing VET (Verifiable Execution Traces), a formal framework that achieves host-independent authentication of agent outputs and takes a step toward host-independent autonomy. Central to VET is the Agent Identity Document (AID), which specifies an agent's configuration together with the proof systems required for verification. VET is compositional: it supports multiple proof mechanisms, including trusted hardware, succinct cryptographic proofs, and notarized TLS transcripts (Web Proofs). We implement VET for an API-based LLM agent and evaluate our instantiation on realistic workloads. We find that for today's black-box, secret-bearing API calls, Web Proofs appear to be the most practical choice, with overhead typically under 3$\times$ compared to direct API calls, while for public API calls, a lower-overhead TEE Proxy is often sufficient. As a case study, we deploy a verifiable trading agent that produces proofs for each decision and composes Web Proofs with a TEE Proxy. Our results demonstrate that practical, host-agnostic authentication is already possible with current technology, laying the foundation for future systems that achieve full host-independent autonomy.

---

### Dynamical Mechanisms for Coordinating Long-term Working Memory Based on the Precision of Spike-timing in Cortical Neurons

Authors: Terrence J. Sejnowski
Published: 2025-12-17
Categories: q-bio.NC, cs.AI
arXiv: https://arxiv.org/abs/2512.15891v8

In the last century, most sensorimotor studies of cortical neurons relied on average firing rates. Rate coding is efficient for fast sensorimotor processing that occurs within a few seconds. Much less is known about the neural mechanisms underlying long-term working memory with a time scale of hours. Cognitive states may not have sensory or motor correlates. For example, you can sit in a quiet room making plans without moving or sensory processing. You can also make plans while out walking. In this perspective, I make the case for a possible second tier of neural activity that coexists with the well-established sensorimotor tier. The prominent physiological feature of the second tier is coordinated spike timing activity. The interplay of data supporting this hypothesis involves three puzzling yet highly intriguing experimental observations, without any obvious indication that they might actually represent different aspects of a single functional organization. First, consider the precision of spiking in individual neurons. The discovery of millisecond-precision spike initiation in cortical neurons was unexpected (Mainen and Sejnowski, 1995). Even more striking was the precision of spiking in vivo, in response to rapidly fluctuating sensory inputs. Second, high temporal resolution can also mediate spike timing-dependent plasticity (STDP) by controlling the relative timing of presynaptic and postsynaptic spikes at the millisecond scale. Third, we observe waves across many frequency bands traveling across the cortex. Strikingly, their timing is highly precise. Gamma waves, for example, which are triggered by attention, can plausibly trigger STDP that lasts for hours in cortical neurons. This temporary cortical network, ostensibly a second tier of functionality, rides astride the long-term sensorimotor network and could support cognitive processing and long-term working memory.

---

### Seeing Beyond Words: Self-Supervised Visual Learning for Multimodal Large Language Models

Authors: Davide Caffagni, Sara Sarto, Marcella Cornia, Lorenzo Baraldi, Pier Luigi Dovesi, Shaghayegh Roohi, Mark Granroth-Wilding, Rita Cucchiara
Published: 2025-12-17
Categories: cs.CV, cs.AI, cs.CL, cs.MM
arXiv: https://arxiv.org/abs/2512.15885v1

Multimodal Large Language Models (MLLMs) have recently demonstrated impressive capabilities in connecting vision and language, yet their proficiency in fundamental visual reasoning tasks remains limited. This limitation can be attributed to the fact that MLLMs learn visual understanding primarily from textual descriptions, which constitute a subjective and inherently incomplete supervisory signal. Furthermore, the modest scale of multimodal instruction tuning compared to massive text-only pre-training leads MLLMs to overfit language priors while overlooking visual details. To address these issues, we introduce JARVIS, a JEPA-inspired framework for self-supervised visual enhancement in MLLMs. Specifically, we integrate the I-JEPA learning paradigm into the standard vision-language alignment pipeline of MLLMs training. Our approach leverages frozen vision foundation models as context and target encoders, while training the predictor, implemented as the early layers of an LLM, to learn structural and semantic regularities from images without relying exclusively on language supervision. Extensive experiments on standard MLLM benchmarks show that JARVIS consistently improves performance on vision-centric benchmarks across different LLM families, without degrading multimodal reasoning abilities. Our source code is publicly available at: https://github.com/aimagelab/JARVIS.

---

### Large Video Planner Enables Generalizable Robot Control

Authors: Boyuan Chen, Tianyuan Zhang, Haoran Geng, Caiyi Zhang, Peihao Li, Kiwhan Song, William T. Freeman, Jitendra Malik, Pieter Abbeel, Russ Tedrake, Vincent Sitzmann, Yilun Du
Published: 2025-12-17
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2512.15840v2

General-purpose robots require decision-making models that generalize across diverse tasks and environments. Recent works build robot foundation models by extending multimodal large language models (MLLMs) with action outputs, creating vision-language-action (VLA) systems. These efforts are motivated by the intuition that MLLMs' large-scale language and image pretraining can be effectively transferred to the action output modality. In this work, we explore an alternative paradigm of using large-scale video pretraining as a primary modality for building robot foundation models. Unlike static images and language, videos capture spatio-temporal sequences of states and actions in the physical world that are naturally aligned with robotic behavior. We curate an internet-scale video dataset of human activities and task demonstrations, and train, for the first time at a foundation-model scale, an open video model for generative robotics planning. The model produces zero-shot video plans for novel scenes and tasks, which we post-process to extract executable robot actions. We evaluate task-level generalization through third-party selected tasks in the wild and real-robot experiments, demonstrating successful physical execution. Together, these results show robust instruction following, strong generalization, and real-world feasibility. We release both the model and dataset to support open, reproducible video-based robot learning. Our website is available at https://www.boyuan.space/large-video-planner/.

---

### Optimizing Agentic Language Model Inference via Speculative Tool Calls

Authors: Daniel Nichols, Prajwal Singhania, Charles Jekel, Abhinav Bhatele, Harshitha Menon
Published: 2025-12-17
Categories: cs.PL, cs.AI, cs.DC, cs.PF, cs.SE
arXiv: https://arxiv.org/abs/2512.15834v1

Language models (LMs) are becoming increasingly dependent on external tools. LM-based agentic frameworks frequently interact with their environment via such tools to search files, run code, call APIs, etc. Further, modern reasoning-based LMs use tools such as web search and Python code execution to enhance their reasoning capabilities. While tools greatly improve the capabilities of LMs, they also introduce performance bottlenecks during the inference process. In this paper, we introduce novel systems optimizations to address such performance bottlenecks by speculating tool calls and forcing sequences to remain resident in the inference engine to minimize overheads. Our optimizations lead to throughput improvements of several hundred tokens per second when hosting inference for LM agents. We provide a theoretical analysis of our algorithms to provide insights into speculation configurations that will yield the best performance. Further, we recommend a new "tool cache" API endpoint to enable LM providers to easily adopt these optimizations.

---

### From Minutes to Days: Scaling Intracranial Speech Decoding with Supervised Pretraining

Authors: Linnea Evanson, Mingfang Zhang, Hubert Banville, Saarang Panchavati, Pierre Bourdillon, Jean-Rémi King
Published: 2025-12-17
Categories: cs.SD, cs.CL, q-bio.NC
arXiv: https://arxiv.org/abs/2512.15830v1

Decoding speech from brain activity has typically relied on limited neural recordings collected during short and highly controlled experiments. Here, we introduce a framework to leverage week-long intracranial and audio recordings from patients undergoing clinical monitoring, effectively increasing the training dataset size by over two orders of magnitude. With this pretraining, our contrastive learning model substantially outperforms models trained solely on classic experimental data, with gains that scale log-linearly with dataset size. Analysis of the learned representations reveals that, while brain activity represents speech features, its global structure largely drifts across days, highlighting the need for models that explicitly account for cross-day variability. Overall, our approach opens a scalable path toward decoding and modeling brain representations in both real-life and controlled task settings.

---

### Human-like working memory signatures emerge from intrinsically plastic artificial neurons for robust dynamic vision

Authors: Jingli Liu, Huannan Zheng, Bohao Zou, Kezhou Yang
Published: 2025-12-17
Categories: cs.ET, cs.AI, cs.CV, cs.NE
arXiv: https://arxiv.org/abs/2512.15829v4

While the unsustainable energy cost of artificial intelligence necessitates physics-driven computing, its performance superiority over full-precision GPUs remains a challenge. We bridge this gap by repurposing the Joule-heating relaxation dynamics of magnetic tunnel junctions, conventionally suppressed as noise, into neuronal intrinsic plasticity, realizing working memory with human-like features. Traditional AI utilizes energy-intensive digital memory that accumulates historical noise in dynamic environments. Conversely, our Intrinsic Plasticity Network (IPNet) leverages thermodynamic dissipation as a temporal filter. We provide direct system-level evidence that this physics-driven memory yields an 18x error reduction compared to spatiotemporal convolutional models in dynamic vision tasks, reducing memory-energy overhead by >90,000x. In autonomous driving, IPNet reduces prediction errors by 12.4% versus recurrent networks. This establishes a neuromorphic paradigm that shatters efficiency limits and surpasses conventional algorithmic performance.

---

### State-Augmented Graphs for Circular Economy Triage

Authors: Richard Fox, Rui Li, Gustav Jonsson, Farzaneh Goli, Miying Yang, Emel Aktas, Yongjing Wang
Published: 2025-12-17
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.15824v2

Circular economy (CE) triage is the assessment of products to determine which sustainable pathway they can follow once they reach the end of their usefulness as they are currently being used. Effective CE triage requires adaptive decisions that balance retained value against the costs and constraints of processing and labour. This paper presents a novel decision-making framework as a simple deterministic solver over a state-augmented Disassembly Sequencing Planning (DSP) graph. By encoding the disassembly history into the state, our framework enforces the Markov property, enabling optimal, recursive evaluation by ensuring each decision only depends on the previous state. The triage decision involves choices between continuing disassembly or committing to a CE option. The model integrates condition-aware utility based on diagnostic health scores and complex operational constraints. We demonstrate the framework's flexibility with a worked example: the hierarchical triage of electric vehicle (EV) batteries, where decisions are driven by the recursive valuation of components. The example illustrates how a unified formalism enables the accommodation of varying mechanical complexity, safety requirements, and economic drivers. This unified formalism therefore provides a tractable and generalisable foundation for optimising CE triage decisions across diverse products and operational contexts.

---

### Secure AI-Driven Super-Resolution for Real-Time Mixed Reality Applications

Authors: Mohammad Waquas Usmani, Sankalpa Timilsina, Michael Zink, Susmit Shannigrahi
Published: 2025-12-17
Categories: cs.CR, cs.LG, cs.MM, eess.IV
arXiv: https://arxiv.org/abs/2512.15823v3

Immersive formats such as 360° and 6DoF point cloud videos require high bandwidth and low latency, posing challenges for real-time AR/VR streaming. This work focuses on reducing bandwidth consumption and encryption/decryption delay, two key contributors to overall latency. We design a system that downsamples point cloud content at the origin server and applies partial encryption. At the client, the content is decrypted and upscaled using an ML-based super-resolution model. Our evaluation demonstrates a nearly linear reduction in bandwidth/latency, and encryption/decryption overhead with lower downsampling resolutions, while the super-resolution model effectively reconstructs the original full-resolution point clouds with minimal error and modest inference time.

---

### BioimageAIpub: a toolbox for AI-ready bioimaging data publishing

Authors: Stefan Dvoretskii, Anwai Archit, Constantin Pape, Josh Moore, Marco Nolden
Published: 2025-12-17
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2512.15820v1

Modern bioimage analysis approaches are data hungry, making it necessary for researchers to scavenge data beyond those collected within their (bio)imaging facilities. In addition to scale, bioimaging datasets must be accompanied with suitable, high-quality annotations and metadata. Although established data repositories such as the Image Data Resource (IDR) and BioImage Archive offer rich metadata, their contents typically cannot be directly consumed by image analysis tools without substantial data wrangling. Such a tedious assembly and conversion of (meta)data can account for a dedicated amount of time investment for researchers, hindering the development of more powerful analysis tools. Here, we introduce BioimageAIpub, a workflow that streamlines bioimaging data conversion, enabling a seamless upload to HuggingFace, a widely used platform for sharing machine learning datasets and models.

---

### A Neurosymbolic Approach to Loop Invariant Generation via Weakest Precondition Reasoning

Authors: Daragh King, Vasileios Koutavas, Laura Kovacs
Published: 2025-12-17
Categories: cs.PL, cs.AI, cs.LO
arXiv: https://arxiv.org/abs/2512.15816v1

Loop invariant generation remains a critical bottleneck in automated program verification. Recent work has begun to explore the use of Large Language Models (LLMs) in this area, yet these approaches tend to lack a reliable and structured methodology, with little reference to existing program verification theory. This paper presents NeuroInv, a neurosymbolic approach to loop invariant generation. NeuroInv comprises two key modules: (1) a neural reasoning module that leverages LLMs and Hoare logic to derive and refine candidate invariants via backward-chaining weakest precondition reasoning, and (2) a verification-guided symbolic module that iteratively repairs invariants using counterexamples from OpenJML. We evaluate NeuroInv on a comprehensive benchmark of 150 Java programs, encompassing single and multiple (sequential) loops, multiple arrays, random branching, and noisy code segments. NeuroInv achieves a $99.5\%$ success rate, substantially outperforming the other evaluated approaches. Additionally, we introduce a hard benchmark of $10$ larger multi-loop programs (with an average of $7$ loops each); NeuroInv's performance in this setting demonstrates that it can scale to more complex verification scenarios.

---

### CodeMem: Architecting Reproducible Agents via Dynamic MCP and Procedural Memory

Authors: Nishant Gaurav, Adit Akarsh, Tejas Ravishankar, Manoj Bajaj
Published: 2025-12-17
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2512.15813v1

Current tool-using AI agents suffer from limited action space, context inefficiency, and probabilistic instability that makes them unsuitable for handling repetitive tasks which are otherwise reliably and efficiently tackled by agentic workflows built on platforms like n8n and Zapier. Earlier works like CodeAct, DynaSaur, Code Mode have tried to tackle the first two issues by using the whole Python language as its action space: The number of tools that the agent can call becomes infinite. Python code blocks can execute complex actions into a single step and print only relevant results which helps in keeping the context lean. However, the probabilistic instability issue still remains, as for the same task in the same environment, the agent can follow different trajectories due to the probabilistic nature of LLMs. Therefore, we need procedural memory for consistency and reliability. This paper proposes CodeMem, an architecture to implement procedural memory via code which can be used to build and run reusable agentic workflows with deterministic reliability.

---

### Foundation Models in Biomedical Imaging: Turning Hype into Reality

Authors: Amgad Muneer, Kai Zhang, Ibraheem Hamdi, Rizwan Qureshi, Muhammad Waqas, Shereen Fouad, Hazrat Ali, Syed Muhammad Anwar, Jia Wu
Published: 2025-12-17
Categories: q-bio.QM, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2512.15808v2

Foundation models (FMs) are driving a prominent shift in biomedical imaging from task-specific models to unified backbone models for diverse tasks. This opens an avenue to integrate imaging, pathology, clinical records, and genomics data into a composite system. However, this vision contrasts sharply with modern medicine's trajectory toward more granular sub-specialization. This tension, coupled with data scarcity, domain heterogeneity, and limited interpretability, creates a gap between benchmark success and real-world clinical value. We argue that the immediate role of FMs lies in augmenting, not replacing, clinical expertise. To separate hype from reality, we introduce REAL-FM (Real-world Evaluation and Assessment of Foundation Models), a multi-dimensional framework for assessing data, technical readiness, clinical value, workflow integration, and responsible AI. Using REAL-FM, we find that while FMs excel in pattern recognition, they fall short in causal reasoning, domain robustness, and safety. Clinical translation is hindered by scarce representative data for model training, unverified generalization beyond oversimplified benchmark settings, and a lack of prospective outcome-based validation. We further examine FM reasoning paradigms, including sequential logic, spatial understanding, and symbolic domain knowledge. We envision that the path forward lies not in a monolithic medical oracle, but in coordinated subspecialist AI systems that are transparent, safe, and clinically grounded.

---

### Spatia: Video Generation with Updatable Spatial Memory

Authors: Jinjing Zhao, Fangyun Wei, Zhening Liu, Hongyang Zhang, Chang Xu, Yan Lu
Published: 2025-12-17
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.15716v1

Existing video generation models struggle to maintain long-term spatial and temporal consistency due to the dense, high-dimensional nature of video signals. To overcome this limitation, we propose Spatia, a spatial memory-aware video generation framework that explicitly preserves a 3D scene point cloud as persistent spatial memory. Spatia iteratively generates video clips conditioned on this spatial memory and continuously updates it through visual SLAM. This dynamic-static disentanglement design enhances spatial consistency throughout the generation process while preserving the model's ability to produce realistic dynamic entities. Furthermore, Spatia enables applications such as explicit camera control and 3D-aware interactive editing, providing a geometrically grounded framework for scalable, memory-driven video generation.

---

### In Pursuit of Pixel Supervision for Visual Pre-training

Authors: Lihe Yang, Shang-Wen Li, Yang Li, Xinjie Lei, Dong Wang, Abdelrahman Mohamed, Hengshuang Zhao, Hu Xu
Published: 2025-12-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.15715v1

At the most basic level, pixels are the source of the visual information through which we perceive the world. Pixels contain information at all levels, ranging from low-level attributes to high-level concepts. Autoencoders represent a classical and long-standing paradigm for learning representations from pixels or other raw inputs. In this work, we demonstrate that autoencoder-based self-supervised learning remains competitive today and can produce strong representations for downstream tasks, while remaining simple, stable, and efficient. Our model, codenamed "Pixio", is an enhanced masked autoencoder (MAE) with more challenging pre-training tasks and more capable architectures. The model is trained on 2B web-crawled images with a self-curation strategy with minimal human curation. Pixio performs competitively across a wide range of downstream tasks in the wild, including monocular depth estimation (e.g., Depth Anything), feed-forward 3D reconstruction (i.e., MapAnything), semantic segmentation, and robot learning, outperforming or matching DINOv3 trained at similar scales. Our results suggest that pixel-space self-supervised learning can serve as a promising alternative and a complement to latent-space approaches.

---

### DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models

Authors: Lunbin Zeng, Jingfeng Yao, Bencheng Liao, Hongyuan Tao, Wenyu Liu, Xinggang Wang
Published: 2025-12-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.15713v3

Diffusion-based decoding has recently emerged as an appealing alternative to autoregressive (AR) generation, offering the potential to update multiple tokens in parallel and reduce latency. However, diffusion vision language models (dVLMs) still lag significantly behind mainstream autoregressive vision language models. This is due to the scarcity and weaker performance of base diffusion language models (dLLMs) compared with their autoregressive counterparts. This raises a natural question: Can we build high-performing dVLMs directly from existing powerful AR models, without relying on dLLMs? We propose DiffusionVL, a family of dVLMs obtained by translating pretrained AR models into the diffusion paradigm via an efficient diffusion finetuning procedure that changes the training objective and decoding process while keeping the backbone architecture intact. Through an efficient diffusion finetuning strategy, we successfully adapt AR pretrained models into the diffusion paradigm. This approach yields two key observations: (1) The paradigm shift from AR-based multimodal models to diffusion is remarkably effective. (2) Direct conversion of an AR language model to a dVLM is also feasible, achieving performance comparable to that of the same AR model finetuned with standard autoregressive visual instruction tuning. To enable practical open-ended generation, we further integrate block decoding, which supports arbitrary-length outputs and KV-cache reuse for faster inference. Our experiments demonstrate that despite training with less than 5% of the data required by prior methods, DiffusionVL achieves a comprehensive performance improvement, with a 34.4% gain on the MMMU-Pro (vision) benchmark and 37.5% gain on the MME (Cog.) benchmark, alongside a 2x inference speedup. The model and code are released at https://github.com/hustvl/DiffusionVL.

---

### Predictive Concept Decoders: Training Scalable End-to-End Interpretability Assistants

Authors: Vincent Huang, Dami Choi, Daniel D. Johnson, Sarah Schwettmann, Jacob Steinhardt
Published: 2025-12-17
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2512.15712v1

Interpreting the internal activations of neural networks can produce more faithful explanations of their behavior, but is difficult due to the complex structure of activation space. Existing approaches to scalable interpretability use hand-designed agents that make and test hypotheses about how internal activations relate to external behavior. We propose to instead turn this task into an end-to-end training objective, by training interpretability assistants to accurately predict model behavior from activations through a communication bottleneck. Specifically, an encoder compresses activations to a sparse list of concepts, and a decoder reads this list and answers a natural language question about the model. We show how to pretrain this assistant on large unstructured data, then finetune it to answer questions. The resulting architecture, which we call a Predictive Concept Decoder, enjoys favorable scaling properties: the auto-interp score of the bottleneck concepts improves with data, as does the performance on downstream applications. Specifically, PCDs can detect jailbreaks, secret hints, and implanted latent concepts, and are able to accurately surface latent user attributes.

---

### Gaussian Pixel Codec Avatars: A Hybrid Representation for Efficient Rendering

Authors: Divam Gupta, Anuj Pahuja, Nemanja Bartolovic, Tomas Simon, Forrest Iandola, Giljoo Nam
Published: 2025-12-17
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2512.15711v1

We present Gaussian Pixel Codec Avatars (GPiCA), photorealistic head avatars that can be generated from multi-view images and efficiently rendered on mobile devices. GPiCA utilizes a unique hybrid representation that combines a triangle mesh and anisotropic 3D Gaussians. This combination maximizes memory and rendering efficiency while maintaining a photorealistic appearance. The triangle mesh is highly efficient in representing surface areas like facial skin, while the 3D Gaussians effectively handle non-surface areas such as hair and beard. To this end, we develop a unified differentiable rendering pipeline that treats the mesh as a semi-transparent layer within the volumetric rendering paradigm of 3D Gaussian Splatting. We train neural networks to decode a facial expression code into three components: a 3D face mesh, an RGBA texture, and a set of 3D Gaussians. These components are rendered simultaneously in a unified rendering engine. The networks are trained using multi-view image supervision. Our results demonstrate that GPiCA achieves the realism of purely Gaussian-based avatars while matching the rendering performance of mesh-based avatars.

---

### Artism: AI-Driven Dual-Engine System for Art Generation and Critique

Authors: Shuai Liu, Yiqing Tian, Yang Chen, Mar Canet Sola
Published: 2025-12-17
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.15710v1

This paper proposes a dual-engine AI architectural method designed to address the complex problem of exploring potential trajectories in the evolution of art. We present two interconnected components: AIDA (an artificial artist social network) and the Ismism Machine, a system for critical analysis. The core innovation lies in leveraging deep learning and multi-agent collaboration to enable multidimensional simulations of art historical developments and conceptual innovation patterns. The framework explores a shift from traditional unidirectional critique toward an intelligent, interactive mode of reflexive practice. We are currently applying this method in experimental studies on contemporary art concepts. This study introduces a general methodology based on AI-driven critical loops, offering new possibilities for computational analysis of art.

---

### Multi-View Foundation Models

Authors: Leo Segre, Or Hirschorn, Shai Avidan
Published: 2025-12-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.15708v2

Foundation models are vital tools in various Computer Vision applications. They take as input a single RGB image and output a deep feature representation that is useful for various applications. However, in case we have multiple views of the same 3D scene, they operate on each image independently and do not always produce consistent features for the same 3D point. We propose a way to convert a Foundation Model into a Multi-View Foundation Model. Such a model takes as input a set of images and outputs a feature map for each image such that the features of corresponding points are as consistent as possible. This approach bypasses the need to build a consistent 3D model of the features and allows direct manipulation in the image space. Specifically, we show how to augment Transformers-based foundation models (i.e., DINO, SAM, CLIP) with intermediate 3D-aware attention layers that help match features across different views. As leading examples, we show surface normal estimation and multi-view segmentation tasks. Quantitative experiments show that our method improves feature matching considerably compared to current foundation models.

---

### GateFusion: Hierarchical Gated Cross-Modal Fusion for Active Speaker Detection

Authors: Yu Wang, Juhyung Ha, Frangil M. Ramirez, Yuchen Wang, David J. Crandall
Published: 2025-12-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.15707v1

Active Speaker Detection (ASD) aims to identify who is currently speaking in each frame of a video. Most state-of-the-art approaches rely on late fusion to combine visual and audio features, but late fusion often fails to capture fine-grained cross-modal interactions, which can be critical for robust performance in unconstrained scenarios. In this paper, we introduce GateFusion, a novel architecture that combines strong pretrained unimodal encoders with a Hierarchical Gated Fusion Decoder (HiGate). HiGate enables progressive, multi-depth fusion by adaptively injecting contextual features from one modality into the other at multiple layers of the Transformer backbone, guided by learnable, bimodally-conditioned gates. To further strengthen multimodal learning, we propose two auxiliary objectives: Masked Alignment Loss (MAL) to align unimodal outputs with multimodal predictions, and Over-Positive Penalty (OPP) to suppress spurious video-only activations. GateFusion establishes new state-of-the-art results on several challenging ASD benchmarks, achieving 77.8% mAP (+9.4%), 86.1% mAP (+2.9%), and 96.1% mAP (+0.5%) on Ego4D-ASD, UniTalk, and WASD benchmarks, respectively, and delivering competitive performance on AVA-ActiveSpeaker. Out-of-domain experiments demonstrate the generalization of our model, while comprehensive ablations show the complementary benefits of each component.

---

### Learning Model Parameter Dynamics in a Combination Therapy for Bladder Cancer from Sparse Biological Data

Authors: Kayode Olumoyin, Lamees El Naqa, Katarzyna Rejniak
Published: 2025-12-17
Categories: cs.LG, q-bio.CB
arXiv: https://arxiv.org/abs/2512.15706v1

In a mathematical model of interacting biological organisms, where external interventions may alter behavior over time, traditional models that assume fixed parameters usually do not capture the evolving dynamics. In oncology, this is further exacerbated by the fact that experimental data are often sparse and sometimes are composed of a few time points of tumor volume. In this paper, we propose to learn time-varying interactions between cells, such as those of bladder cancer tumors and immune cells, and their response to a combination of anticancer treatments in a limited data scenario. We employ the physics-informed neural network (PINN) approach to predict possible subpopulation trajectories at time points where no observed data are available. We demonstrate that our approach is consistent with the biological explanation of subpopulation trajectories. Our method provides a framework for learning evolving interactions among biological organisms when external interventions are applied to their environment.

---

### Dynamic Rebatching for Efficient Early-Exit Inference with DREX

Authors: Xuting Liu, Daniel Alexander, Siva Kesava Reddy Kakarla, Behnaz Arzani, Vincent Liu
Published: 2025-12-17
Categories: cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2512.15705v1

Early-Exit (EE) is a Large Language Model (LLM) architecture that accelerates inference by allowing easier tokens to be generated using only a subset of the model's layers. However, traditional batching frameworks are ill-suited for EE LLMs, as not all requests in a batch may be ready to exit at the same time. Existing solutions either force a uniform decision on the batch, which overlooks EE opportunities, or degrade output quality by forcing premature exits. We propose Dynamic Rebatching, a solution where we dynamically reorganize the batch at each early-exit point. Requests that meet the exit criteria are immediately processed, while those that continue are held in a buffer, re-grouped into a new batch, and forwarded to deeper layers. We introduce DREX, an early-exit inference system that implements Dynamic Rebatching with two key optimizations: 1) a copy-free rebatching buffer that avoids physical data movement, and 2) an EE and SLA-aware scheduler that analytically predicts whether a given rebatching operation will be profitable. DREX also efficiently handles the missing KV cache from skipped layers using memory-efficient state-copying. Our evaluation shows that DREX improves throughput by 2-12% compared to baseline approaches while maintaining output quality. Crucially, DREX completely eliminates involuntary exits, providing a key guarantee for preserving the output quality intended by the EE model.

---

### End-to-End Training for Autoregressive Video Diffusion via Self-Resampling

Authors: Yuwei Guo, Ceyuan Yang, Hao He, Yang Zhao, Meng Wei, Zhenheng Yang, Weilin Huang, Dahua Lin
Published: 2025-12-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.15702v2

Autoregressive video diffusion models hold promise for world simulation but are vulnerable to exposure bias arising from the train-test mismatch. While recent works address this via post-training, they typically rely on a bidirectional teacher model or discriminator. To achieve an end-to-end solution, we introduce Resampling Forcing, a teacher-free framework that enables training autoregressive video models from scratch and at scale. Central to our approach is a self-resampling scheme that simulates inference-time model errors on history frames during training. Conditioned on these degraded histories, a sparse causal mask enforces temporal causality while enabling parallel training with frame-level diffusion loss. To facilitate efficient long-horizon generation, we further introduce history routing, a parameter-free mechanism that dynamically retrieves the top-k most relevant history frames for each query. Experiments demonstrate that our approach achieves performance comparable to distillation-based baselines while exhibiting superior temporal consistency on longer videos owing to native-length training.

---

### VLIC: Vision-Language Models As Perceptual Judges for Human-Aligned Image Compression

Authors: Kyle Sargent, Ruiqi Gao, Philipp Henzler, Charles Herrmann, Aleksander Holynski, Li Fei-Fei, Jiajun Wu, Jason Zhang
Published: 2025-12-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.15701v1

Evaluations of image compression performance which include human preferences have generally found that naive distortion functions such as MSE are insufficiently aligned to human perception. In order to align compression models to human perception, prior work has employed differentiable perceptual losses consisting of neural networks calibrated on large-scale datasets of human psycho-visual judgments. We show that, surprisingly, state-of-the-art vision-language models (VLMs) can replicate binary human two-alternative forced choice (2AFC) judgments zero-shot when asked to reason about the differences between pairs of images. Motivated to exploit the powerful zero-shot visual reasoning capabilities of VLMs, we propose Vision-Language Models for Image Compression (VLIC), a diffusion-based image compression system designed to be post-trained with binary VLM judgments. VLIC leverages existing techniques for diffusion model post-training with preferences, rather than distilling the VLM judgments into a separate perceptual loss network. We show that calibrating this system on VLM judgments produces competitive or state-of-the-art performance on human-aligned visual compression depending on the dataset, according to perceptual metrics and large-scale user studies. We additionally conduct an extensive analysis of the VLM-based reward design and training procedure and share important insights. More visuals are available at https://kylesargent.github.io/vlic

---

### FrontierCS: Evolving Challenges for Evolving Intelligence

Authors: Qiuyang Mang, Wenhao Chai, Zhifei Li, Huanzhi Mao, Shang Zhou, Alexander Du, Hanchen Li, Shu Liu, Edwin Chen, Yichuan Wang, Xieting Chu, Zerui Cheng et al.
Published: 2025-12-17
Categories: cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2512.15699v1

We introduce FrontierCS, a benchmark of 156 open-ended problems across diverse areas of computer science, designed and reviewed by experts, including CS PhDs and top-tier competitive programming participants and problem setters. Unlike existing benchmarks that focus on tasks with known optimal solutions, FrontierCS targets problems where the optimal solution is unknown, but the quality of a solution can be objectively evaluated. Models solve these tasks by implementing executable programs rather than outputting a direct answer. FrontierCS includes algorithmic problems, which are often NP-hard variants of competitive programming problems with objective partial scoring, and research problems with the same property. For each problem we provide an expert reference solution and an automatic evaluator. Combining open-ended design, measurable progress, and expert curation, FrontierCS provides a benchmark at the frontier of computer-science difficulty. Empirically, we find that frontier reasoning models still lag far behind human experts on both the algorithmic and research tracks, that increasing reasoning budgets alone does not close this gap, and that models often over-optimize for generating merely workable code instead of discovering high-quality algorithms and system designs.

---

### Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning

Authors: Yifei Li, Wenzhao Zheng, Yanran Zhang, Runze Sun, Yu Zheng, Lei Chen, Jie Zhou, Jiwen Lu
Published: 2025-12-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.15693v2

The misuse of AI-driven video generation technologies has raised serious social concerns, highlighting the urgent need for reliable AI-generated video detectors. However, most existing methods are limited to binary classification and lack the necessary explanations for human interpretation. In this paper, we present Skyra, a specialized multimodal large language model (MLLM) that identifies human-perceivable visual artifacts in AI-generated videos and leverages them as grounded evidence for both detection and explanation. To support this objective, we construct ViF-CoT-4K for Supervised Fine-Tuning (SFT), which represents the first large-scale AI-generated video artifact dataset with fine-grained human annotations. We then develop a two-stage training strategy that systematically enhances our model's spatio-temporal artifact perception, explanation capability, and detection accuracy. To comprehensively evaluate Skyra, we introduce ViF-Bench, a benchmark comprising 3K high-quality samples generated by over ten state-of-the-art video generators. Extensive experiments demonstrate that Skyra surpasses existing methods across multiple benchmarks, while our evaluation yields valuable insights for advancing explainable AI-generated video detection.

---

### mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs

Authors: Jonas Pai, Liam Achenbach, Victoriano Montesinos, Benedek Forrai, Oier Mees, Elvis Nava
Published: 2025-12-17
Categories: cs.RO, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2512.15692v2

Prevailing Vision-Language-Action Models (VLAs) for robotic manipulation are built upon vision-language backbones pretrained on large-scale, but disconnected static web data. As a result, despite improved semantic generalization, the policy must implicitly infer complex physical dynamics and temporal dependencies solely from robot trajectories. This reliance creates an unsustainable data burden, necessitating continuous, large-scale expert data collection to compensate for the lack of innate physical understanding. We contend that while vision-language pretraining effectively captures semantic priors, it remains blind to physical causality. A more effective paradigm leverages video to jointly capture semantics and visual dynamics during pretraining, thereby isolating the remaining task of low-level control. To this end, we introduce mimic-video, a novel Video-Action Model (VAM) that pairs a pretrained Internet-scale video model with a flow matching-based action decoder conditioned on its latent representations. The decoder serves as an Inverse Dynamics Model (IDM), generating low-level robot actions from the latent representation of video-space action plans. Our extensive evaluation shows that our approach achieves state-of-the-art performance on simulated and real-world robotic manipulation tasks, improving sample efficiency by 10x and convergence speed by 2x compared to traditional VLA architectures.

---

### Multi-Modal Semantic Communication

Authors: Matin Mortaheb, Erciyes Karakaya, Sennur Ulukus
Published: 2025-12-17
Categories: cs.LG, cs.IT, eess.SP, eess.SY
arXiv: https://arxiv.org/abs/2512.15691v1

Semantic communication aims to transmit information most relevant to a task rather than raw data, offering significant gains in communication efficiency for applications such as telepresence, augmented reality, and remote sensing. Recent transformer-based approaches have used self-attention maps to identify informative regions within images, but they often struggle in complex scenes with multiple objects, where self-attention lacks explicit task guidance. To address this, we propose a novel Multi-Modal Semantic Communication framework that integrates text-based user queries to guide the information extraction process. Our proposed system employs a cross-modal attention mechanism that fuses visual features with language embeddings to produce soft relevance scores over the visual data. Based on these scores and the instantaneous channel bandwidth, we use an algorithm to transmit image patches at adaptive resolutions using independently trained encoder-decoder pairs, with total bitrate matching the channel capacity. At the receiver, the patches are reconstructed and combined to preserve task-critical information. This flexible and goal-driven design enables efficient semantic communication in complex and bandwidth-constrained environments.

---

### BashArena: A Control Setting for Highly Privileged AI Agents

Authors: Adam Kaufman, James Lucassen, Tyler Tracy, Cody Rushing, Aryan Bhatt
Published: 2025-12-17
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2512.15688v1

Future AI agents might run autonomously with elevated privileges. If these agents are misaligned, they might abuse these privileges to cause serious damage. The field of AI control develops techniques that make it harder for misaligned AIs to cause such damage, while preserving their usefulness. We introduce BashArena, a setting for studying AI control techniques in security-critical environments. BashArena contains 637 Linux system administration and infrastructure engineering tasks in complex, realistic environments, along with four sabotage objectives (execute malware, exfiltrate secrets, escalate privileges, and disable firewall) for a red team to target. We evaluate multiple frontier LLMs on their ability to complete tasks, perform sabotage undetected, and detect sabotage attempts. Claude Sonnet 4.5 successfully executes sabotage while evading monitoring by GPT-4.1 mini 26% of the time, at 4% trajectory-wise FPR. Our findings provide a baseline for designing more effective control protocols in BashArena. We release the dataset as a ControlArena setting and share our task generation pipeline.

---

### Can LLMs Guide Their Own Exploration? Gradient-Guided Reinforcement Learning for LLM Reasoning

Authors: Zhenwen Liang, Sidi Lu, Wenhao Yu, Kishan Panaganti, Yujun Zhou, Haitao Mi, Dong Yu
Published: 2025-12-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.15687v1

Reinforcement learning has become essential for strengthening the reasoning abilities of large language models, yet current exploration mechanisms remain fundamentally misaligned with how these models actually learn. Entropy bonuses and external semantic comparators encourage surface level variation but offer no guarantee that sampled trajectories differ in the update directions that shape optimization. We propose G2RL, a gradient guided reinforcement learning framework in which exploration is driven not by external heuristics but by the model own first order update geometry. For each response, G2RL constructs a sequence level feature from the model final layer sensitivity, obtainable at negligible cost from a standard forward pass, and measures how each trajectory would reshape the policy by comparing these features within a sampled group. Trajectories that introduce novel gradient directions receive a bounded multiplicative reward scaler, while redundant or off manifold updates are deemphasized, yielding a self referential exploration signal that is naturally aligned with PPO style stability and KL control. Across math and general reasoning benchmarks (MATH500, AMC, AIME24, AIME25, GPQA, MMLUpro) on Qwen3 base 1.7B and 4B models, G2RL consistently improves pass@1, maj@16, and pass@k over entropy based GRPO and external embedding methods. Analyzing the induced geometry, we find that G2RL expands exploration into substantially more orthogonal and often opposing gradient directions while maintaining semantic coherence, revealing that a policy own update space provides a far more faithful and effective basis for guiding exploration in large language model reinforcement learning.

---

### A Multivariate Statistical Framework for Detection, Classification and Pre-localization of Anomalies in Water Distribution Networks

Authors: Oleg Melnikov, Yurii Dorofieiev, Yurii Shakhnovskiy, Huy Truong, Victoria Degeler
Published: 2025-12-17
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.15685v1

This paper presents a unified framework, for the detection, classification, and preliminary localization of anomalies in water distribution networks using multivariate statistical analysis. The approach, termed SICAMS (Statistical Identification and Classification of Anomalies in Mahalanobis Space), processes heterogeneous pressure and flow sensor data through a whitening transformation to eliminate spatial correlations among measurements. Based on the transformed data, the Hotelling's $T^2$ statistic is constructed, enabling the formulation of anomaly detection as a statistical hypothesis test of network conformity to normal operating conditions. It is shown that Hotelling's $T^2$ statistic can serve as an integral indicator of the overall "health" of the system, exhibiting correlation with total leakage volume, and thereby enabling approximate estimation of water losses via a regression model. A heuristic algorithm is developed to analyze the $T^2$ time series and classify detected anomalies into abrupt leaks, incipient leaks, and sensor malfunctions. Furthermore, a coarse leak localization method is proposed, which ranks sensors according to their statistical contribution and employs Laplacian interpolation to approximate the affected region within the network. Application of the proposed framework to the BattLeDIM L-Town benchmark dataset demonstrates high sensitivity and reliability in leak detection, maintaining robust performance even under multiple leaks. These capabilities make the method applicable to real-world operational environments without the need for a calibrated hydraulic model.

---

### High-Dimensional Partial Least Squares: Spectral Analysis and Fundamental Limitations

Authors: Victor Léger, Florent Chatelain
Published: 2025-12-17
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2512.15684v2

Partial Least Squares (PLS) is a widely used method for data integration, designed to extract latent components shared across paired high-dimensional datasets. Despite decades of practical success, a precise theoretical understanding of its behavior in high-dimensional regimes remains limited. In this paper, we study a data integration model in which two high-dimensional data matrices share a low-rank common latent structure while also containing individual-specific components. We analyze the singular vectors of the associated cross-covariance matrix using tools from random matrix theory and derive asymptotic characterizations of the alignment between estimated and true latent directions. These results provide a quantitative explanation of the reconstruction performance of the PLS variant based on Singular Value Decomposition (PLS-SVD) and identify regimes where the method exhibits counter-intuitive or limiting behavior. Building on this analysis, we compare PLS-SVD with principal component analysis applied separately to each dataset and show its asymptotic superiority in detecting the common latent subspace. Overall, our results offer a comprehensive theoretical understanding of high-dimensional PLS-SVD, clarifying both its advantages and fundamental limitations.

---

### Stylized Synthetic Augmentation further improves Corruption Robustness

Authors: Georg Siedel, Rojan Regmi, Abhirami Anand, Weijia Shao, Silvia Vock, Andrey Morozov
Published: 2025-12-17
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2512.15675v3

This paper proposes a training data augmentation pipeline that combines synthetic image data with neural style transfer in order to address the vulnerability of deep vision models to common corruptions. We show that although applying style transfer on synthetic images degrades their quality with respect to the common Frechet Inception Distance (FID) metric, these images are surprisingly beneficial for model training. We conduct a systematic empirical analysis of the effects of both augmentations and their key hyperparameters on the performance of image classifiers. Our results demonstrate that stylization and synthetic data complement each other well and can be combined with popular rule-based data augmentation techniques such as TrivialAugment, while not working with others. Our method achieves state-of-the-art corruption robustness on several small-scale image classification benchmarks, reaching 93.54%, 74.9% and 50.86% robust accuracy on CIFAR-10-C, CIFAR-100-C and TinyImageNet-C, respectively

---

### Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers

Authors: Adam Karvonen, James Chua, Clément Dumas, Kit Fraser-Taliente, Subhash Kantamneni, Julian Minder, Euan Ong, Arnab Sen Sharma, Daniel Wen, Owain Evans, Samuel Marks
Published: 2025-12-17
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.15674v2

Large language model (LLM) activations are notoriously difficult to understand, with most existing techniques using complex, specialized methods for interpreting them. Recent work has proposed a simpler approach known as LatentQA: training LLMs to directly accept LLM activations as inputs and answer arbitrary questions about them in natural language. However, prior work has focused on narrow task settings for both training and evaluation. In this paper, we instead take a generalist perspective. We evaluate LatentQA-trained models, which we call Activation Oracles (AOs), in far out-of-distribution settings and examine how performance scales with training data diversity. We find that AOs can recover information fine-tuned into a model (e.g., biographical knowledge or malign propensities) that does not appear in the input text, despite never being trained with activations from a fine-tuned model. Our main evaluations are four downstream tasks where we can compare to prior white- and black-box techniques. We find that even narrowly-trained LatentQA models can generalize well, and that adding additional training datasets (such as classification tasks and a self-supervised context prediction task) yields consistent further improvements. Our best AOs match or exceed white-box baselines on all four tasks and the best overall baseline on 3 of 4. These results suggest that diversified training to answer natural-language queries imparts a general capability to verbalize information about LLM activations.

---

### Explaining the Reasoning of Large Language Models Using Attribution Graphs

Authors: Chase Walker, Rickard Ewetz
Published: 2025-12-17
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2512.15663v1

Large language models (LLMs) exhibit remarkable capabilities, yet their reasoning remains opaque, raising safety and trust concerns. Attribution methods, which assign credit to input features, have proven effective for explaining the decision making of computer vision models. From these, context attributions have emerged as a promising approach for explaining the behavior of autoregressive LLMs. However, current context attributions produce incomplete explanations by directly relating generated tokens to the prompt, discarding inter-generational influence in the process. To overcome these shortcomings, we introduce the Context Attribution via Graph Explanations (CAGE) framework. CAGE introduces an attribution graph: a directed graph that quantifies how each generation is influenced by both the prompt and all prior generations. The graph is constructed to preserve two properties-causality and row stochasticity. The attribution graph allows context attributions to be computed by marginalizing intermediate contributions along paths in the graph. Across multiple models, datasets, metrics, and methods, CAGE improves context attribution faithfulness, achieving average gains of up to 40%.

---

### Stepwise Think-Critique: Interleaved Reasoning and Self-Critique in a Single LLM

Authors: Jiaqi Xu, Cuiling Lan, Xuejin Chen, Yan Lu
Published: 2025-12-17
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.15662v4

Human beings solve complex problems through critical thinking, where reasoning and evaluation are intertwined to converge toward correct solutions. However, most existing large language models (LLMs) treat the reasoning and verification as separate processes: they either generate reasoning without explicit self-checking or rely on external verifiers to detect errors post hoc. The former lacks immediate feedback, while the latter increases system complexity and hinders synchronized learning. Motivated by human critical thinking, we propose Stepwise Think-Critique (STC), an end-to-end trainable framework in which a single LLM emits a structured, step-level critique inline with each reasoning step. STC is trained with reinforcement learning that complements reasoning rewards with a critique-consistency reward derived from final-answer correctness, jointly optimizing reasoning correctness and critique reliability. On five mathematical reasoning benchmarks, STC improves Pass@1 by 7.2% over the 1.5B base model and attains 67.4% step-level critique F1, surpassing seven external process reward models evaluated at their per-dataset oracle thresholds---a step toward LLMs with built-in critical thinking.

---

### Prospects for quantum advantage in machine learning from the representability of functions

Authors: Sergi Masot-Llima, Elies Gil-Fuster, Carlos Bravo-Prieto, Jens Eisert, Tommaso Guaita
Published: 2025-12-17
Categories: quant-ph, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2512.15661v2

Demonstrating quantum advantage in machine learning tasks requires navigating a complex landscape of proposed models and algorithms. To bring clarity to this search, we introduce a framework that connects the structure of parametrized quantum circuits to the mathematical nature of the functions they can actually learn. Within this framework, we show how fundamental properties, like circuit depth and non-Clifford gate count, directly determine whether a model's output leads to efficient classical simulation or surrogation. We argue that this analysis uncovers common pathways to dequantization that underlie many existing simulation methods. More importantly, it reveals critical distinctions between models that are fully simulatable, those whose function space is classically tractable, and those that remain robustly quantum. This perspective provides a conceptual map of this landscape, clarifying how different models relate to classical simulability and pointing to where opportunities for quantum advantage may lie.

---

### PPSEBM: An Energy-Based Model with Progressive Parameter Selection for Continual Learning

Authors: Xiaodi Li, Dingcheng Li, Rujun Gao, Mahmoud Zamani, Feng Mi, Latifur Khan
Published: 2025-12-17
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.15658v1

Continual learning remains a fundamental challenge in machine learning, requiring models to learn from a stream of tasks without forgetting previously acquired knowledge. A major obstacle in this setting is catastrophic forgetting, where performance on earlier tasks degrades as new tasks are learned. In this paper, we introduce PPSEBM, a novel framework that integrates an Energy-Based Model (EBM) with Progressive Parameter Selection (PPS) to effectively address catastrophic forgetting in continual learning for natural language processing tasks. In PPSEBM, progressive parameter selection allocates distinct, task-specific parameters for each new task, while the EBM generates representative pseudo-samples from prior tasks. These generated samples actively inform and guide the parameter selection process, enhancing the model's ability to retain past knowledge while adapting to new tasks. Experimental results on diverse NLP benchmarks demonstrate that PPSEBM outperforms state-of-the-art continual learning methods, offering a promising and robust solution to mitigate catastrophic forgetting.

---

### SoFlow: Solution Flow Models for One-Step Generative Modeling

Authors: Tianze Luo, Haotian Yuan, Zhuang Liu
Published: 2025-12-17
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2512.15657v2

The multi-step denoising process in diffusion and Flow Matching models causes major efficiency issues, which motivates research on few-step generation. We present Solution Flow Models (SoFlow), a framework for one-step generation from scratch. By analyzing the relationship between the velocity function and the solution function of the velocity ordinary differential equation (ODE), we propose a Flow Matching loss and a solution consistency loss to train our models. The Flow Matching loss allows our models to provide estimated velocity fields for Classifier-Free Guidance (CFG) during training, which improves generation performance. Notably, our consistency loss does not require the calculation of the Jacobian-vector product (JVP), a common requirement in recent works that is not well-optimized in deep learning frameworks like PyTorch. Experimental results indicate that, when trained from scratch using the same Diffusion Transformer (DiT) architecture and an equal number of training epochs, our models achieve better FID-50K scores than MeanFlow models on the ImageNet 256x256 dataset.

---

### Characterizing Mamba's Selective Memory using Auto-Encoders

Authors: Tamanna Hossain, Robert L. Logan, Ganesh Jagadeesan, Sameer Singh, Joel Tetreault, Alejandro Jaimes
Published: 2025-12-17
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.15653v1

State space models (SSMs) are a promising alternative to transformers for language modeling because they use fixed memory during inference. However, this fixed memory usage requires some information loss in the hidden state when processing long sequences. While prior work has studied the sequence length at which this information loss occurs, it does not characterize the types of information SSM language models (LMs) tend to forget. In this paper, we address this knowledge gap by identifying the types of tokens (e.g., parts of speech, named entities) and sequences (e.g., code, math problems) that are more frequently forgotten by SSM LMs. We achieve this by training an auto-encoder to reconstruct sequences from the SSM's hidden state, and measure information loss by comparing inputs with their reconstructions. We perform experiments using the Mamba family of SSM LMs (130M--1.4B) on sequences ranging from 4--256 tokens. Our results show significantly higher rates of information loss on math-related tokens (e.g., numbers, variables), mentions of organization entities, and alternative dialects to Standard American English. We then examine the frequency that these tokens appear in Mamba's pretraining data and find that less prevalent tokens tend to be the ones Mamba is most likely to forget. By identifying these patterns, our work provides clear direction for future research to develop methods that better control Mamba's ability to retain important information.

---

### A Statistical Framework for Spatial Boundary Estimation and Change Detection: Application to the Sahel Sahara Climate Transition

Authors: Stephen Tivenan, Indranil Sahoo, Yanjun Qian
Published: 2025-12-17
Categories: stat.AP, stat.ML
arXiv: https://arxiv.org/abs/2512.15650v1

Spatial boundaries, such as ecological transitions or climatic regime interfaces, capture steep environmental gradients, and shifts in their structure can signal emerging environmental changes. Quantifying uncertainty in spatial boundary locations and formally testing for temporal shifts remains challenging, especially when boundaries are derived from noisy, gridded environmental data. We present a unified framework that combines heteroskedastic Gaussian process (GP) regression with a scaled Maximum Absolute Difference (MAD) Global Envelope Test (GET) to estimate spatial boundary curves and assess whether they evolve over time. The heteroskedastic GP provides a flexible probabilistic reconstruction of boundary lines, capturing spatially varying mean structure and location specific variability, while the test offers a rigorous hypothesis testing tool for detecting departures from expected boundary behaviors. Simulation studies show that the proposed method achieves the correct size under the null and high power for detecting local boundary shifts. Applying our framework to the Sahel Sahara transition zone, using annual Koppen Trewartha climate classifications from 1960 to 1989, we find no statistically significant decade scale changes in the arid and semi arid or semi arid and non arid interfaces. However, the method successfully identifies localized boundary shifts during the extreme drought years of 1983 and 1984, consistent with climate studies documenting regional anomalies in these interfaces during that period.

---

### VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?

Authors: Hongbo Zhao, Meng Wang, Fei Zhu, Wenzhuo Liu, Bolin Ni, Fanhu Zeng, Gaofeng Meng, Zhaoxiang Zhang
Published: 2025-12-17
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2512.15649v2

The computational and memory overheads associated with expanding the context window of LLMs severely limit their scalability. A noteworthy solution is vision-text compression (VTC), exemplified by frameworks like DeepSeek-OCR and Glyph, which convert long texts into dense 2D visual representations, thereby achieving token compression ratios of 3x-20x. However, the impact of this high information density on the core long-context capabilities of vision-language models (VLMs) remains under-investigated. To address this gap, we introduce the first benchmark for VTC and systematically assess the performance of VLMs across three long-context understanding settings: VTC-Retrieval, which evaluates the model's ability to retrieve and aggregate information; VTC-Reasoning, which requires models to infer latent associations to locate facts with minimal lexical overlap; and VTC-Memory, which measures comprehensive question answering within long-term dialogue memory. Furthermore, we establish the VTCBench-Wild to simulate diverse input scenarios.We comprehensively evaluate leading open-source and proprietary models on our benchmarks. The results indicate that, despite being able to decode textual information (e.g., OCR) well, most VLMs exhibit a surprisingly poor long-context understanding ability with VTC-processed information, failing to capture long associations or dependencies in the context.This study provides a deep understanding of VTC and serves as a foundation for designing more efficient and scalable VLMs.

---

### Hard Labels In! Rethinking the Role of Hard Labels in Mitigating Local Semantic Drift

Authors: Jiacheng Cui, Bingkui Tong, Xinyue Bi, Xiaohan Zhao, Jiacheng Liu, Zhiqiang Shen
Published: 2025-12-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.15647v3

Soft labels from teacher models are a de facto practice for knowledge transfer and large-scale dataset distillation (e.g., SRe2L, LPLD). However, when we limit the number of crops per image to reduce the substantial cost of storing precomputed soft labels, these methods suffer severely from local semantic drift: visually ambiguous crops can cause soft supervision to deviate from the image-level ground-truth semantics, leading to persistent errors and a train-test distribution mismatch. We revisit the overlooked role of hard labels and show that, when properly integrated, they can act as a content-invariant semantic anchor that calibrates such drift. We theoretically analyze the emergence of drift under sparse soft-label supervision and demonstrate that hybridizing hard and soft labels restores alignment between visual content and semantic supervision. Building on this insight, we propose a new training paradigm, Hard Label for Alleviating Local Semantic Drift (HALD), which uses hard labels as intermediate corrective signals while preserving the fine-grained benefits of soft labels. Extensive experiments on dataset distillation and large-scale classification benchmarks show consistent generalization improvements. On ImageNet-1K, our method achieves 42.7% accuracy with only 285M soft-label storage (reduces by 100X), outperforming prior state-of-the-art LPLD 9.0%.

---

### Fully Bayesian Spectral Clustering and Benchmarking with Uncertainty Quantification for Small Area Estimation

Authors: Jairo Fúquene-Patiño
Published: 2025-12-17
Categories: stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2512.15643v2

In this work, inspired by machine learning techniques, we propose a new Bayesian model for Small Area Estimation (SAE), the Fay-Herriot model with Spectral Clustering (FH-SC). Unlike traditional approaches, clustering in FH-SC is based on spectral clustering algorithms that utilize external covariates, rather than geographical or administrative criteria. A major advantage of the FH-SC model is its flexibility in integrating existing SAE approaches, with or without clustering random effects. To enable benchmarking, we leverage the theoretical framework of posterior projections for constrained Bayesian inference and derive closed form expressions for the new Rao-Blackwell (RB) estimators of the posterior mean under the FH-SC model. Additionally, we introduce a novel measure of uncertainty for the benchmarked estimator, the Conditional Posterior Mean Square Error (CPMSE), which is generalizable to other Bayesian SAE estimators. We conduct model-based and data-based simulation studies to evaluate the frequentist properties of the CPMSE. The proposed methodology is motivated by a real case study involving the estimation of the proportion of households with internet access in the municipalities of Colombia. Finally, we also illustrate the advantages of FH-SC over existing Bayesian and frequentist approaches through our case study.

---

### IC-Effect: Precise and Efficient Video Effects Editing via In-Context Learning

Authors: Yuanhang Li, Yiren Song, Junzhe Bai, Xinran Liang, Hu Yang, Libiao Jin, Qi Mao
Published: 2025-12-17
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.15635v1

We propose \textbf{IC-Effect}, an instruction-guided, DiT-based framework for few-shot video VFX editing that synthesizes complex effects (\eg flames, particles and cartoon characters) while strictly preserving spatial and temporal consistency. Video VFX editing is highly challenging because injected effects must blend seamlessly with the background, the background must remain entirely unchanged, and effect patterns must be learned efficiently from limited paired data. However, existing video editing models fail to satisfy these requirements. IC-Effect leverages the source video as clean contextual conditions, exploiting the contextual learning capability of DiT models to achieve precise background preservation and natural effect injection. A two-stage training strategy, consisting of general editing adaptation followed by effect-specific learning via Effect-LoRA, ensures strong instruction following and robust effect modeling. To further improve efficiency, we introduce spatiotemporal sparse tokenization, enabling high fidelity with substantially reduced computation. We also release a paired VFX editing dataset spanning $15$ high-quality visual styles. Extensive experiments show that IC-Effect delivers high-quality, controllable, and temporally consistent VFX editing, opening new possibilities for video creation.

---

### How Much is Too Much? Exploring LoRA Rank Trade-offs for Retaining Knowledge and Domain Robustness

Authors: Darshita Rathore, Vineet Kumar, Chetna Bansal, Anindya Moitra
Published: 2025-12-17
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.15634v1

Large language models are increasingly adapted to downstream tasks through fine-tuning. Full supervised fine-tuning (SFT) and parameter-efficient fine-tuning (PEFT) methods, such as Low-Rank Adaptation (LoRA), are two dominant approaches. While PEFT methods are widely used for their computational efficiency, the implications of their configurations (e.g., rank) remain under-explored in downstream Q&A tasks and generalisation. In this work, we perform a comprehensive evaluation across multiple reasoning and recall datasets, conducting a rank sweep to quantify the trade-off between SFT and PEFT. We also compare the accuracy of PEFT and SFT models across in-domain and out-of-domain adaptation, highlighting distinct generalisation behaviour and task-specific forgetting. We demonstrate that LoRA achieves competitive and in some cases superior performance compared to SFT, particularly on reasoning tasks at specific rank values. Additionally, we analyze the internal representations via spectral features and layer-wise attention structures, offering insights into representational drift and structural changes in attention patterns.

---

### Learning continuous state of charge dependent thermal decomposition kinetics for Li-ion cathodes using Kolmogorov-Arnold Chemical Reaction Neural Networks (KA-CRNNs)

Authors: Benjamin C. Koenig, Sili Deng
Published: 2025-12-17
Categories: physics.chem-ph, cs.LG
arXiv: https://arxiv.org/abs/2512.15628v2

Thermal runaway in lithium-ion batteries is strongly influenced by the state of charge (SOC). Existing predictive models typically infer scalar kinetic parameters at a full SOC or a few discrete SOC levels, preventing them from capturing the continuous SOC dependence that governs exothermic behavior during abuse conditions. To address this, we apply the Kolmogorov-Arnold Chemical Reaction Neural Network (KA-CRNN) framework to learn continuous and realistic SOC-dependent exothermic cathode-electrolyte interactions. We apply a physics-encoded KA-CRNN to learn SOC-dependent kinetic parameters for cathode-electrolyte decomposition directly from differential scanning calorimetry (DSC) data. A mechanistically informed reaction pathway is embedded into the network architecture, enabling the activation energies, pre-exponential factors, enthalpies, and related parameters to be represented as continuous and fully interpretable functions of the SOC. The framework is demonstrated for NCA, NM, and NMA cathodes, yielding models that reproduce DSC heat-release features across all SOCs and provide interpretable insight into SOC-dependent oxygen-release and phase-transformation mechanisms. This approach establishes a foundation for extending kinetic parameter dependencies to additional environmental and electrochemical variables, supporting more accurate and interpretable thermal runaway prediction and monitoring.

---

### OccStress: Stress-Testing the 4D Occupancy Forecasting Chain

Authors: Yu Zheng, Jie Hu, Jiaqi Xiong, Ruiping Liu, Junwei Zheng, Kailun Yang, Jiaming Zhang
Published: 2025-12-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.15621v2

Occupancy world models use historical occupancy states to forecast future 3D scenes, but their robustness under corrupted temporal inputs remains poorly understood. Existing evaluations primarily emphasize clean forecasting accuracy and provide limited evidence about how errors enter, persist, and propagate through the occupancy perception-forecasting chain. This paper introduces OccStress, a robustness stress-testing benchmark for the occupancy forecasting chain. OccStress contains 21 corruption families with 61 severity configurations and 10,827 strict temporal anchors across 3 datasets. OccStress covers both 3D occupancy perception and 4D occupancy forecasting through two complementary tracks. This design separates model-mediated pipeline errors under standardized sensor stressors from the intrinsic sensitivity of 4D forecasting models to corrupted occupancy states. OccStress further defines temporal injection protocols to test whether errors in the current state, recent history, or earlier history affect future forecasts differently. OccStress provides aggregate metrics for evaluating robustness along the occupancy forecasting chain. Experiments with five 4D forecasters reveal that current occupancy models are substantially affected by both upstream prediction errors and direct state corruptions, and that clean performance alone is an insufficient description of source- and position-specific robustness. Code, data, and evaluation tools are available at https://insailab.org/OccStress.

---

### Persistent feature reconstruction of resident space objects (RSOs) within inverse synthetic aperture radar (ISAR) images

Authors: Morgan Coe, Gruffudd Jones, Leah-Nani Alconcel, Marina Gashinova
Published: 2025-12-17
Categories: cs.CV, eess.SP
arXiv: https://arxiv.org/abs/2512.15618v1

With the rapidly growing population of resident space objects (RSOs) in the near-Earth space environment, detailed information about their condition and capabilities is needed to provide Space Domain Awareness (SDA). Space-based sensing will enable inspection of RSOs at shorter ranges, independent of atmospheric effects, and from all aspects. The use of a sub-THz inverse synthetic aperture radar (ISAR) imaging and sensing system for SDA has been proposed in previous work, demonstrating the achievement of sub-cm image resolution at ranges of up to 100 km. This work focuses on recognition of external structures by use of sequential feature detection and tracking throughout the aligned ISAR images of the satellites. The Hough transform is employed to detect linear features, which are tracked throughout the sequence. ISAR imagery is generated via a metaheuristic simulator capable of modelling encounters for a variety of deployment scenarios. Initial frame-to-frame alignment is achieved through a series of affine transformations to facilitate later association between image features. A gradient-by-ratio method is used for edge detection within individual ISAR images, and edge magnitude and direction are subsequently used to inform a double-weighted Hough transform to detect features with high accuracy. Feature evolution during sequences of frames is analysed. It is shown that the use of feature tracking within sequences with the proposed approach will increase confidence in feature detection and classification, and an example use-case of robust detection of shadowing as a feature is presented.

---