Artificial Intelligence · Cross-listed from cs.CV
TCLA: Training-Free Class-wise Logit Adaptation for Medical Vision-Language Models
Tianyou Jiang and Ziyu Zhou
Medical
Vision-
Language Models (VLMs) exhibit strong zero-shot performance, yet their effectiveness still declines on out-of-distribution (OOD) data due to domain shifts and class bias inherited from large-scale pretraining. Existing few-shot adaptation methods typically introduce additional trainable components, which can be unstable in extremely low-data regimes (e.g., 1-shot), and lack robustness on different medical data. We present TCLA, a purely training-free few-shot adaptation method for Medical VLMs, which is fast and model-agnostic. TCLA corrects inference logits based on a small set of support samples, boosting pretrained VLMs performance by improving inter-class deconfusion and reducing domain shift. Extensive experiments on nine
datasets across multiple medical imaging modalities including X-ray, Ultrasound, MRI, CT, Histopathology, demonstrate that TCLA consistently improves OOD performance of Medical VLMs and, in most of cases, outperforms existing training-based adaptation methods.
Read the full abstract ▾
Artificial Intelligence
Beyond Fixed Representations: The Vocabulary and Verifier Gaps in Open-Ended AI
Yuan Cao and Haiqian Yang
Modern AI systems are increasingly being evaluated for their ability to reason, code, prove
theorems, use tools, and long-horizon research tasks. These are powerful capabilities, but they share a structural limitation: the representational frame within which the model operates, including its conceptual vocabulary, the space of admissible solutions it can search, and the criteria by which success is evaluated, is typically fixed and supplied in advance. This paper argues that building stronger intelligent systems capable of open-ended innovation requires additional classes of operations: the creation, stabilization, and reuse of new representational primitives, which alter the space being searched rather than simply searching within it. We characterize the distance between current AI systems and genuinely open-ended intelligence through two gaps. The first is the vocabulary gap, the difficulty of inventing and stabilizing new representational primitives rather than merely recombining existing ones. The second is the verifier gap, the difficulty of judging the value of a new primitive when its full payoff may be visible only after future reuse. We interpret both gaps through a unified framework of intelligence as cognitive discrepancy reduction. By viewing intelligent behaviors as a sequence of cognitive transformations, we distinguish intra-space transformations which operate within a fixed representational frame, from generative transformations which may modify the frame itself. On this basis, we propose a ladder of innovation autonomy and outline several directions for advancing open-ended AI, including objectives that reward useful representational change, persistent
memory architectures for invented primitives, and adaptive verification mechanisms capable of evolving alongside the representations they evaluate.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
ALICE: Learning a General-Purpose Pathology Foundation Model from Vision, Vision-Language, and Slide-Level Experts
Jiawen Li, Tian Guan, Huijuan Shi et al. (+5 more)
Foundation models are reshaping computational pathology, yet their capabilities remain shaped by pretraining objectives, data sources, and spatial scales, fragmenting complementary expertise across separate backbones. Here we present ALICE, a unified foundation model trained through multi-stage agglomerative
distillation that sequentially distills eight
vision-only,
vision-
language, and slide-level teacher models into dedicated modules of a single backbone. ALICE is pretrained on 24,985,184 tile-level pathology images and 155,604 high-resolution images, and evaluated across 21 task scenarios, 96 downstream tasks, and 48 data sources, spanning region-of-interest tissue analysis,
vision-
language multimodal evaluation, and whole-slide clinical assessment. In all three evaluation settings, ALICE achieved the best average rank among task-matched pathology foundation models. These results demonstrate that agglomerative
distillation can consolidate complementary capabilities from specialized models into a unified backbone for broad computational pathology applications. The model is available at https://github.com/WonderLandxD/ALICE.
Read the full abstract ▾
All authors Jiawen Li, Tian Guan, Huijuan Shi, Xitong Ling, Mingxi Fu, Anjia Han, Chao He, Yonghong He
Artificial Intelligence
SAGEAgent: A Self-Evolving Agent for Cost-Aware Modality Acquisition in Multimodal Survival Prediction
Chongyu Qu, Can Cui, Zhengyi Lu et al. (+8 more)
Does every cancer patient truly need a complete diagnostic workup for accurate survival prediction? In
multimodal clinical oncology, diagnostic modalities follow a clinically mandated order of escalating burden – from demographics collected at intake to genomic profiling requiring specialized tissue analysis. Current
multimodal survival methods either assume all modalities are available or passively handle missing data, but none actively reason about whether acquiring the next modality is justified for a given patient along this ordered workflow. We formulate this as a sequential decision problem and propose SAGEAgent (Sequential Acquisition Guided by Experience), a self-evolving LLM-based clinical
agent that decides which diagnostic modalities to acquire for each patient, balancing predictive accuracy against clinical invasiveness. SAGEAgent reasons about each patient's evolving diagnostic state through clinical tools that translate numerical predictions into text, an episodic
memory that retrieves similar past cases, and a semantic
memory that accumulates reusable decision patterns from experience. Experiments on a glioma cohort combining TCGA-LGG, TCGA-GBM, and BraTS with four diagnostic modalities demonstrate that SAGEAgent achieves competitive survival prediction accuracy while reducing average acquisition burden by 55%.
Read the full abstract ▾
All authors Chongyu Qu, Can Cui, Zhengyi Lu, Junchao Zhu, Tianyuan Yao, Junlin Guo, Juming Xiong, Yanfan Zhu, Yuechen Yang, Bennett A. Landman, Yuankai Huo
Artificial Intelligence · Cross-listed from cs.CV
Seeing is Free, Speaking is Not: Uncovering the True Energy Bottleneck in Edge VLM Inference
Junfei Zhan, Haoxun Shen, Mingang Guo et al. (+2 more)
Vision-
Language Models (VLMs) are the perceptual backbone of
embodied AI, but their energy footprint on edge hardware remains poorly understood. Existing efficiency efforts focus predominantly on reducing visual
tokens, implicitly treating visual processing as the dominant energy cost. We overturn this implicit assumption through the first systematic energy profiling of on-device VLM inference, spanning five models across three architecture families, four input resolutions, and two hardware platforms (NVIDIA RTX 3070 and Jetson Orin NX). Our analysis yields three findings. First, average inference power is a model-intrinsic constant, invariant to input resolution, image complexity, and
prompt type, with less than 5% variation across all conditions. This means that all energy variation across inputs must arise from variation in inference time, not from variation in power draw. Second, each output
token costs 11 to 39x more wall-clock time than each input
token due to the compute-bound and
memory-bound asymmetry between prefill and decode, making output
token count the dominant driver of both latency and energy. Third, image complexity, measured by the number of objects in an image, induces up to 4.1x energy differences at identical resolution. This variation arises not from increased visual processing cost, but from differences in output length. These findings expose a fundamental limitation of visual
token pruning: even removing all visual
tokens saves at most 10% of total energy for fixed-
token models. Across models spanning 1 billion to 8 billion parameters, controlling output length saves up to 97% of total energy, with the energy dominance of decoding growing stronger at larger model scale. In short, the true energy bottleneck in edge VLM inference is not what the model sees, but how much it says. Code is available at https://github.com/Junfei-Z/seeing-is-free.
Read the full abstract ▾
All authors Junfei Zhan, Haoxun Shen, Mingang Guo, Zixuan Huang, Tengjiao He
Artificial Intelligence · Cross-listed from cs.SE
Failure as a Process: An Anatomy of CLI Coding Agent Trajectories
Xiangxin Zhao, Han Li, Shuaiting Li et al. (+4 more)
Large
language model (LLM) coding
agents are increasingly deployed to autonomously perform software engineering tasks in terminal-based environments, making their reliability a growing concern. Existing empirical studies investigate why coding
agents fail, yet they largely treat failure as a final outcome rather than a temporal process, providing limited insight into how failures emerge, evolve, and become unrecoverable. We present the first large-scale empirical study of CLI coding-
agent failure trajectories, introducing a process-oriented framework that analyzes failure through its onset,
evolution, and recovery across execution trajectories. We first collect 3,843 execution trajectories generated by seven frontier models across three coding-
agent scaffolds (OpenHands, MiniSWE, and Terminus2) on Terminal-Bench, then carefully filter them to obtain 1,794 complete and valid trajectories for manual annotation (over 63,000 execution steps), from which we derive 14 findings spanning failure occurrence, root causes, recovery, and cross-system consistency. Our findings show that coding-
agent failures are predominantly driven by epistemic errors, typically begin within the first few execution steps, and often remain hidden until recovery is no longer possible, suggesting that improving coding-
agent reliability requires earlier validation and intervention rather than relying solely on final-outcome evaluation.
Read the full abstract ▾
All authors Xiangxin Zhao, Han Li, Shuaiting Li, Tianyi Zhao, Earl T. Barr, Federica Sarro, He Ye
Artificial Intelligence · Cross-listed from cs.CV
What VGGT Knows About Overlap: Probing Geometric Foundation Models for Co-Visibility
Filippo Ziliotto, Luciano Serafini, Lamberto Ballan et al. (+1 more)
A fundamental challenge in 3D reconstruction and robotic localization is co-visibility: determining which image pairs share overlapping visible surfaces, particularly in scenarios with minimal overlap. We demonstrate that VGGT implicitly encodes co-visibility as an emergent behavior: without any supervision for this task, its internal representations exhibit a clear hierarchical structure mirroring that of large
language models, i.e. early layers build a 3D-aware scene representation, while late layers act as dedicated co-visibility reasoners. In particular, we identify layer L17 as a negative anchor that consistently routes non-co-visible pairs for this backbone, regardless of the evaluation setting, providing task-grounded evidence of layer specialization in a geometry-grounded foundation model. Building on this, we introduce Co-VGGT, which freezes VGGT and trains only a lightweight layer-wise mixture-of-experts head (less than 7.5M parameters) to classify co-visibility from RGB alone, treating each layer as a specialized expert whose
geometric abstraction is adaptively weighted per input pair. On the Co-
VisiON benchmark, Co-VGGT surpasses the human annotation baseline and improves over prior work by more than 25% pairwise and 10% multiview. Pairwise predictions are well-calibrated (ECE=0.030), enabling direct use as edge weights in visibility graphs for downstream SfM and SLAM pipelines without post-hoc correction. Code and data are available.
Read the full abstract ▾
All authors Filippo Ziliotto, Luciano Serafini, Lamberto Ballan, Tommaso Campari
Artificial Intelligence · Cross-listed from cs.LG
All Explanations are Wrong, But Many Are Useful: Exploring the Rashomon Explanation Set with Large Language Models
Pan Li
Explaining machine-learning models is increasingly important for decision-making and consumer trust, yet it is widely believed to come at a cost: existing Explainable AI (XAI) methods suffer from a persistent accuracy-explainability trade-off. We argue that this trade-off is not fundamental, but an artifact of treating explanation and prediction as separate objectives; when properly coupled, they become complementary, so that equipping a model to explain itself improves, rather than degrades, its accuracy. We introduce the Rashomon Explanation paradigm, which builds a set of faithful, prediction-guiding explanations rather than a single one, and prove that this set is generally non-empty and that explanation fidelity bounds the performance of the models it guides. To explore this set, we propose RashomonLLM, an Explanation-Prediction-Reflection agentic workflow that generates explanations in natural
language by iteratively aligning them with predictions, and we prove it converges and recovers the full set. Across customer-churn classification, clinical survival regression, and industrial click-through prediction on large-scale live-streaming logs, RashomonLLM significantly outperforms state-of-the-art prediction and XAI baselines on both accuracy and explanation quality, with gains driven by explanation fidelity and robust to distribution shifts, temporal splits, and seeds. Our framework thus advances business performance while laying the groundwork for consumer trust.
Read the full abstract ▾
Artificial Intelligence
Shared Selective Persistent Memory for Agentic LLM Systems
Sanjana Pedada, Aditya Dhavala and Neelraj Patil
Agentic LLM systems that generate code through multi-turn tool use face a fundamental context problem: each session starts from zero, discarding the domain constraints, data schemas, tool configurations, and output preferences that made previous sessions productive. We introduce shared selective persistent
memory, an architecture that retains four categories of reusable context - task specifications, data schemas, tool configurations, and output constraints - while discarding session-specific
reasoning traces, and that packages them into workspaces transferable across users under role-based access control. The resulting cost curve is non-monotonic. In a controlled replication on four public
datasets, where a formatting specification is established once and then withheld, no
memory completes 0/12 trials at 3.8K input
tokens, selective
memory completes 12/12 at 3.9K, and full conversation history completes 8/12 at 7.7K. What is kept matters more than how much is kept: the winning configuration costs essentially what the failing one does, and twice as much context does not improve on it. Both differences from no
memory survive Bonferroni-corrected exact McNemar tests (p = 0.0005, p = 0.008); the two
memory conditions separate on price rather than completion. We implement this in a deployed platform where
agents produce git-versioned artifacts from CSV, SQL, REST, and MCP sources. A complementary zero-
token data refresh contract decouples generated programs from runtime data, firing on 12/12 trials at a median 0.08s with no model call, while summary-driven data representation costs 97-431x fewer
tokens than raw injection. Across 24 recurring enterprise tasks selective
memory completes 23/24 against 19/24 and 17/24, though at that sample no pairwise difference reaches significance.
Read the full abstract ▾
Artificial Intelligence
Multimodal Reward Hacking in Reinforcement Learning
Jiayu Yao, Yiwei Wang, Anmeng Zhang et al. (+5 more)
Reinforcement learning (RL) is increasingly used to align
multimodal large
language models (MLLMs), but higher rewards do not always imply better task performance. This risk is amplified when visual evidence is evaluated by text-only or weakly grounded rewards. We study reward hacking in MLLM RL across safety VQA, chart VQA, and stress-test settings, varying reward design, data ambiguity, model scale (2B-32B), and RL
algorithm (GRPO, RLOO, DAPO). We introduce Newly Rewarded Failure Rate (NRFR), which measures failures among samples whose proxy reward improves over the SFT baseline. Outcome-only rewards cause severe hacking, reaching 48.1% Reward Hacking Rate (RHR), while NRFR exceeding RHR shows that RL creates new failures rather than merely inheriting them. Scaling reduces but does not eliminate hacking: even the 32B model retains a 54.9% worse rate under outcome-only rewards, whereas answer-aware rewards improve the oracle trend at every scale. Robustness is also
algorithm- and scale-dependent: GRPO is consistently most resistant, RLOO remains vulnerable, and DAPO improves substantially from 2B to 8B. Visual-evidence rewards help only with reliable verification: keyword-based checks increase hacking, while VLM-as-judge semantic verification reduces it. Overall,
multimodal reward hacking is a systematic result of optimizing imperfect rewards, and robust
alignment requires rewards and verifiers that remain reliable under optimization pressure.
Read the full abstract ▾
All authors Jiayu Yao, Yiwei Wang, Anmeng Zhang, Zhe Sun, Songsong Wang, Lingrui Mei, Yuyao Ge, Shenghua Liu
Artificial Intelligence
Ceci n'est pas une pipe: AI systems as semantic abstractions
Jade Alglave and Patrick Cousot
An AI system's output is not the fact or world state it appears to describe, but rather an engineered representation. We propose a semantic framework to describe AI systems, to be able to examine the correctness of such representations. To do so, we distinguish what is justified by accepted domain knowledge, what reference sources say, and what the system can currently use. This allows us to give precise definitions to common failures: extrapolation, refuted or unsupported assertion, sources versus knowledge mismatch, stale or refuted source, added hypotheses, unsupported use... We hope our framework gives a useful vocabulary for specifying and checking AI systems whose outputs, citations, tool calls, and world-changing actions must be justified by reliable claims and explicit authority rather than apparent fluency.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Decoupling Language Guidance from Backbones for Text-Guided Medical Segmentation
Yungeng Liu, Xuanzi Fang, Haijin Zeng et al. (+2 more)
Text-guided medical image
segmentation leverages clinical semantics to improve lesion delineation, yet many existing models bind cross-modal fusion, supervision, and decoder design into a task-specific architecture. Such tight coupling makes it difficult to reuse
language guidance modules across heterogeneous
vision and text backbones, and often requires redesigning the network when the encoder pair changes. This paper presents BTHA, a backbone-transferable hierarchical adapter framework for text-guided medical image
segmentation. BTHA is built around a stable feature-level interface: given multi-scale visual features and a text representation, it injects semantic guidance through shape-preserving adapters while maintaining the decoder-side tensor contract. To make this interface effective, we introduce a Hierarchical Coarse-to-Fine Supervision Strategy that decomposes learning into global image-text
alignment, multi-scale auxiliary localization, and boundary-aware final mask refinement. We further design a Scale-Adaptive Gated Semantic Guidance (SAGSG) adapter, where resolution-specific gates adaptively control textual injection and channel recalibration suppresses redundant cross-modal responses. Evaluations across diverse
vision and text backbones show that the same adapter and supervision design remains effective across convolutional and
transformer-based visual encoders as well as different
language encoders. Experiments on four public
datasets further demonstrate that BTHA improves strong text-guided baselines with modest computational overhead.
Read the full abstract ▾
All authors Yungeng Liu, Xuanzi Fang, Haijin Zeng, Qi Dai, Yongyong Chen
Artificial Intelligence
ProofCouncil: An LLM Agent for Solving Open Mathematical Problems
Johannes Schmitt, Tim Gehrunger, Jasper Dekoninck et al. (+4 more)
Large
language models (LLMs) have shown increasing promise in solving open problems in mathematics. However, their performance can be further improved through agentic workflows tailored to real-world mathematical practice. To this end, we introduce ProofCouncil, a mathematical
agent that is designed to tackle open problems using an author-critic architecture. ProofCouncil served as a submission to the second batch of FirstProof, a challenge consisting of 10 real-world mathematical problems that
agents must solve autonomously. Its submissions for 6 of the 10 problems were judged by the referees to be correct up to at most minor revisions, showing the best performance among participating teams. We also evaluate ProofCouncil on 30 open problems collected from mathematical researchers. Among the 21 solutions that received human feedback, 5 were judged completely correct, 2 more were judged promising pending final verification, and a further 8 contained useful partial progress. In this short paper, we describe the development of ProofCouncil and the
agent-building library used to create it, which we release as open source to the community.
Read the full abstract ▾
All authors Johannes Schmitt, Tim Gehrunger, Jasper Dekoninck, Gergely Bérczi, Uri Kreitner, Liam Price, David Holmes
Artificial Intelligence · Cross-listed from cs.SE
Practical Source Code Recovery from Binary Functions Using Anchor-Based Retrieval and LLM Reasoning
Charles Edward Gagnon, Steven H. H. Ding, Philippe Charland et al. (+1 more)
We present a practical pipeline for recovering source code from stripped binary functions by combining reverse engineering, anchor-based source code
retrieval, and large
language model
reasoning. Our binary-to-source-code
retrieval method attempts to identify the source function from a source code database, rather than generating approximate decompiled pseudocode. It extracts anchors such as strings, constants, external calls, and available function names using Ghidra, retrieves candidate files via an inverted-index search database, narrows candidates to likely function snippets, and re-ranks them with a large
language model (LLM) based on disassembly, decompiled code, and source metadata. Confident matches can also serve as anchors in later passes. In an evaluation backed by our high-fidelity source code database on a stripped, optimized tcpdump binary, our proposed binary-to-source matching method achieves 95.2% assembly instruction coverage. Experiments on a GitHub-based
retrieval database showed lower performance with 35.5% instruction coverage on average, mainly due to
retrieval misses. These results show that source-level binary recovery excels with high-quality databases and remains a useful tool in noisy environments.
Read the full abstract ▾
All authors Charles Edward Gagnon, Steven H. H. Ding, Philippe Charland, Benjamin C. M. Fung
Artificial Intelligence
How Does Bayesian Causal Discovery Fail? Characterising Structural Consequences in Linear Gaussian Networks under Latent Confounding
Debargha Ghosh, Silja Renooij and Anna V. Kononova
Bayesian causal discovery is widely used for its ability to quantify epistemic uncertainty over directed acyclic graphs (DAGs) through posterior inference. However, its behaviour under latent confounding remains poorly understood, as existing work typically notes that confounding breaks identifiability without characterising how the posterior distribution over DAGs responds. In this work, we analyse posterior behaviour under latent confounding in linear Gaussian causal models, focusing on additive latent confounding between exactly two observed variables. We derive a critical correlation threshold above which the score function favours graphs with a spurious edge between the confounded variables, and show that this threshold decreases with sample size – more data lowers the correlation required for the spurious edge to be favoured. Beyond this threshold, we characterize two distinct posterior failure regimes determined by the local structure around the confounded variables. Our findings are supported by exact posterior computations on multiple graph structures, demonstrating both the predicted failure regimes.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Parameter-Efficient Vision-Language Adaptation with Continuous Metadata Conditioning for Animal Re-Identification
Anil Osman Tur, Tonje Knutsen Sordalen, Kim Tallaksen Halvorsen et al. (+1 more)
Long-term animal re-identification (ReID) must remain robust to gradual morphological
evolution and seasonal appearance shifts. Although recent
vision-
language models provide strong pretrained visual representations, adapting them to longitudinal ecological settings remains challenging, particularly under identity and temporal distribution shifts. We present a parameter-efficient CLIP adaptation framework for animal ReID and introduce a continuous metadata-conditioning mechanism that incorporates numerical attributes directly into the
prompt representation during training. While low-rank visual adaptation,
prompt-based supervision, and cross-modal
alignment provide the adaptation framework, the proposed metadata-conditioning strategy constitutes the primary methodological contribution. By preserving the continuous structure of numerical metadata rather than discretizing it into textual categories, the proposed approach enables smooth modulation of the
embedding space during training while maintaining a purely visual inference pipeline. Experiments on a seven-year longitudinal fish
dataset and multiple wildlife
benchmarks demonstrate improved performance under closed-set, open-set, and time-aware evaluation protocols. The results demonstrate that continuous metadata conditioning improves robustness to longitudinal appearance variation and temporal distribution shifts, while parameter-efficient adaptation enables a purely visual inference pipeline without requiring metadata at test time. Code and evaluation splits can be found at: https://github.com/AnilOsmanTur/MetaPrompt-ReID.
Read the full abstract ▾
All authors Anil Osman Tur, Tonje Knutsen Sordalen, Kim Tallaksen Halvorsen, Cigdem Beyan
Artificial Intelligence · Cross-listed from cs.CL
Test-Time Scaling for Small VLMs on Multilingual Visual MCQ
Spiros Baxevanakis and Peng-Jian Yang
Test-time scaling (TTS) reliably improves
reasoning in large
language models, but whether it transfers to small open
vision-
language models remains unclear. We examine this on EXAMS-V, a
multilingual visual multiple-choice
benchmark, comparing self-consistency, describe-then-reason with PRM-guided beam search, and two post-hoc selectors across Qwen2.5-VL-7B-Instruct and Qwen3.5-4B. What matters is the conditions under which TTS runs, not the search or verification machinery. The largest factor is parseability: an early
prompt format left many chains
reasoning correctly yet never committing to an answer letter, which a standard answer cue and a guided repair step largely remove. A larger decoding budget removes the rest: raising the per-chain
token limit from 1k to 2k recovers 3.7 pp, whereas sampling more chains (8 to 16) adds only 0.15 pp. Once chains have room to finish, elaborate methods contribute little: PRM-guided beam search trails plain self-consistency by 0.39 pp at over eight times the cost, and neither a training-free generative critic nor a trained
multimodal PRM beats majority vote across both policies. The largest gain comes instead from the policy model itself (+11.4 pp). Our best configuration reaches 84.1% on the held-out ImageCLEF 2026 test split, ranking first on the Visual MCQ leaderboard.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
A Sovereign, Open-Source Foundation Model for German and English
Soofi-Team: Benedikt Droste, David Fitzek, Ruben Härle et al. (+28 more)
We present Soofi S 30B-A3B, a sovereign, open-source Mixture-of-Experts (MoE) hybrid Mamba
Transformer foundation model for German and English. Its hybrid design activates only 3B of 30B parameters per
token and keeps the inference cache near-constant as context grows, giving it a decisive throughput advantage over dense models for long-context, high-concurrency deployment. Pretrained on roughly 27 trillion
tokens with deliberately up-weighted German, Soofi S matches dense 14 to 27B models on aggregate English and German
benchmarks while achieving the best code aggregates in both
languages among 17 open base models, and outperforms every European sovereign baseline in our comparison, including ones far larger in active parameters. Among fully open models, Soofi S obtains the highest English and German evaluation scores, ahead of Olmo 3 32B and Apertus 70B. Soofi S was built end-to-end on the German Industrial AI Cloud, a sovereign HPC scale AI infrastructure operated by Deutsche Telekom in Munich. Soofi S will be released under highly permissive, open-access terms: weights, selected intermediate checkpoints, full per-source data accounting, hyperparameters, and training and evaluation code. Where source licenses permit, data-construction artifacts are released under permissive licenses; commercially licensed sources are documented with aggregate statistics and exact mixture accounting.
Read the full abstract ▾
All authors Soofi-Team: Benedikt Droste, David Fitzek, Ruben Härle, Lukas Helff, Maximilian Idahl, Alex Jude, Abbas Goher Khan, Maurice Kraus, Timm Ruland, Richard Rutmann, Sebastian Sztwiertnia, Markus Frey, Daniil Gurgurov, Jan Pfister, Tom Röhr, Sebastian von Rohrscheidt, Jörg Bienert, Nicolas Flores-Herr, Simon Gottschalk, Andreas Hotho, Kristian Kersting, Joachim Köhler, Alexander Löser, Wolfgang Nejdl, Simon Ostermann, Jan Plogsties, Björn Plüster, Patrick Putzky, Mehdi Ali, Michael Fromm, Max Lübbering
Artificial Intelligence · Cross-listed from cs.CV
SVF-CR: Synchronized Visual-Facial Cross-Refinement for Multimodal Ambivalence and Hesitancy Recognition
Hyein Park, Namho Kim and Junhwa Kim
Ambivalence and hesitancy are subtle behavioral states that are expressed through a combination of verbal content, facial behavior, visual context, and acoustic cues. Effective recognition therefore requires not only extracting informative unimodal representations, but also modeling how temporally aligned behavioral evidence interacts across modalities. In this paper, we propose a synchronized visual-facial cross-refinement framework (SVF-CR) with pairwise
multimodal evidence fusion for ambivalence and hesitancy recognition. The proposed method first extracts whole-
video segment
tokens and cropped-face segment
tokens using the same temporal partition. The synchronized visual and facial
tokens are refined through intra-modal self-
attention and bidirectional visual-facial cross-
attention, allowing whole-
video context and local facial behavior to mutually refine each other before evidence construction. We then construct segment-level visual-facial evidence using consistency and discrepancy modeling, followed by temporal self-
attention and
attention pooling. Textual and acoustic features are lightly refined through context self-
attention and are fused with the enhanced visual-facial evidence at the final decision stage using pairwise evidence fusion. Experiments on the BAH (Behavioral Ambivalence/Hesitancy) public evaluation split show that the proposed synchronized visual-facial cross-refinement improves public macro-F1 over both global visual-face
token fusion and synchronized evidence baselines, achieving a public macro-F1 of 0.7156. Code is available at : https://github.com/hiinnnii/BAH-Challenge-ECCV2026\_SVF-CR.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Self-Guided Test-Time Training for Long-Context LLMs
Xinyu Zhu, Zhe Xu, Xiaohan Wei et al. (+10 more)
Long-context processing has become increasingly important for large
language models (LLMs), but simply extending the context window does not guarantee effective utilization of long inputs. As input length grows, accuracy often degrades, indicating that models still struggle to identify and use the evidence most relevant to a question. A promising way to improve long-context utilization is test-time training (TTT), which treats the test context as a training example for instance-specific parameter adaptation. However, applying TTT to the entire long context is prohibitively expensive, while adapting on randomly sampled spans introduces severe noise. Because most spans in a long context are irrelevant to the specific question, training on them may even degrade the base model's performance. Our preliminary study shows that TTT is highly sensitive to training-span quality: on LongBench-v2, TTT on randomly sampled spans hurts performance, whereas TTT on oracle spans substantially improves it. Motivated by this, we propose a simple method, Self-Guided TTT (S-TTT): before adaptation, the model identifies the evidence spans it should learn from, and the standard
language-modeling training objective is applied only to those selected spans. On two challenging long-context
reasoning benchmarks, LongBench-v2 and LongBench-Pro, S-TTT improves accuracy for both Qwen3-4B-Thinking-2507 and Llama-3.1-8B-Instruct, achieving up to a 15% relative improvement.
Read the full abstract ▾
All authors Xinyu Zhu, Zhe Xu, Xiaohan Wei, Yunchen Pu, Fei Tian, Chonglin Sun, Kaushik Rangadurai, Hua Zhi, Frank Shyu, Sandeep Pandey, Luke Simon, Yu Meng, Xi Liu
Artificial Intelligence
Fictional Worldbuilding: Multi-Agent LLM Collaboration with Hierarchical Context Compression and Iterative Review
Jingbo Chen, He Wang, Wei Yuan et al. (+2 more)
Worldbuilding, the construction of coherent fictional worlds, is a foundational task in game design and literary creation. Large
Language Models (LLMs) offer new possibilities for automated content generation, but their application to worldbuilding faces three challenges: context explosion that grows linearly with the building process, the tension between creative diversity and content consistency, and the absence of automated quality assurance. This paper presents AutoWorldBuilder, a multi-
agent collaborative system that addresses these challenges through five integrated components: a structured concept network with conflict detection; a DAG-based hybrid batch scheduler that groups tasks by semantic locality; a four-layer context compression mechanism achieving approximately 90%
token reduction; an iterative review system with specialized Auditor
agents that improves proposal pass rates from 42% to over 85%; and a skill-driven
agent architecture supporting zero-code extension with differentiated temperature configuration. Two experiments across 20 diverse worldbuilding tasks, using GPT-OSS 120B and DeepSeek v3.2 as LLM backends, demonstrate a 95.0% success rate. The system generated 56-103 self-consistent concepts per world in 18-31 minutes with zero-conflict delivery. The architectural patterns validated here, including layer-as-budget compression, semantic-locality scheduling, and separation of generation and review, transfer to the broader class of knowledge-intensive, multi-
agent LLM applications.
Read the full abstract ▾
All authors Jingbo Chen, He Wang, Wei Yuan, Yuqiao Lai, Zhenyan Lu
Artificial Intelligence · Cross-listed from cs.LG
On-Device Adaptive Battery Power Prediction for Electric Vehicles
Avik Bhatnagar, Anton Paule, Tobias Schuermann et al. (+2 more)
Adaptive power management in Electric Vehicles (EVs) requires accurate power prediction. Although deep learning models have emerged as highly effective for time-series
forecasting in this domain, their performance is prone to degradation when exposed to data with distributions different from the training data. We introduce a novel approach that enables on-device learning in resource-constrained EV systems to continuously adapt pretrained battery prediction models to new, unseen data. We leverage existing pretrained models by transforming them into adaptable versions that retain critical hyperparameter knowledge from their initial training. We comprehensively investigate both online and offline model adaptation strategies. Our results demonstrate significant improvements in
forecasting performance across various models and time horizons, achieving mean absolute error reductions of up to 7.49% and 14.88% with online and offline adaptation techniques, respectively. This study highlights the substantial benefit of on-device adaptation, resulting in enhanced battery power predictions than unadapted model deployments in real-world EV scenarios.
Read the full abstract ▾
All authors Avik Bhatnagar, Anton Paule, Tobias Schuermann, Sebastian Reiter, Oliver Bringmann
Artificial Intelligence · Cross-listed from cs.LG
Fully Trainable Deep Differentiable Logic Gate Networks and Lookup Table Networks
Wout Mommen, Lars Keuninckx, Matthias Hartmann et al. (+2 more)
We introduce a novel method for both partial and full optimization of the connections in deep differentiable logic gate networks (LGNs) and lookup table networks (LUTNs). Our training method utilizes a probability distribution over a set of connections per gate/lookup table (LUT) input pin, selecting the connection with highest merit, all whilst the optimal gate types or LUT-entries are learned in parallel. We show that the connection-optimized LGNs outperform standard fixed-connection LGNs on the Yin-Yang, MNIST Handwritten Digits and Fashion-MNIST
benchmarks, while requiring only a fraction of the number of logic gates. We achieve 98.92% on the MNIST
dataset with two layers of 8000 gates. With only one layer of 8000 gates, we obtain 98.45%, showing that our method requires almost 50 times fewer gates compared to fixed-connection LGNs. Training stability up to ten layers has been ensured by employing a high learning rate, straight-through
estimators and trimming constant-output gate types. Additionally, we present a LUT
neuron description that enables stable training with backpropagation, tested up to 6-layer deep networks. The model requires four times fewer trainable parameters and still achieves a higher accuracy compared to the fixed-connection LGN training
algorithm. Our connection-training
algorithm also works well for the LUTNs, achieving an accuracy of 98.88% for two layers of 2000 6-input LUTs.
Read the full abstract ▾
All authors Wout Mommen, Lars Keuninckx, Matthias Hartmann, Werner Van Leekwijck, Piet Wambacq
Artificial Intelligence · Cross-listed from cs.DC
STEEL: Sparsity-Aware Fused Attention for Energy-Efficient Long-Sequence Inference on AMD's XDNA NPU
Victor J.B. Jung, Gagandeep Singh, Joseph Melber et al. (+3 more)
The growing adoption of large
language model-based
agents within operating system workflows has increased the importance of energy-efficient inference on laptop-class systems-on-chip (SoCs). While cloud offloading remains common, it introduces reliability and
privacy concerns that are particularly problematic for agentic workloads. Recent laptop SoCs, therefore, incorporate neural processing engines (NPUs) optimized for energy efficiency; however, effectively mapping
attention mechanisms onto NPUs remains challenging due to architectural diversity and explicit data-movement programming models. In this work, we present STEEL, the first open-source implementation of FlashAttention targeting XDNA-like NPUs. STEEL introduces a dataflow formulation of prefill
attention, enabling efficient exploitation of spatial parallelism and on-chip
memory. Furthermore, STEEL addresses the load imbalance induced by the causal mask by leveraging a sparsity-aware pipeline placement onto the NPU array, reducing synchronization overhead and improving utilization. We evaluate STEEL on the AMD Ryzen AI 9 HX 370 SoC and compare its performance against optimized CPU and GPU implementations. Experimental results show that STEEL reduces energy consumption by an average of 9.17x and 1.75x relative to CPU and GPU baselines, respectively. On XDNA 1, STEEL achieves an average 9.6x latency reduction over the prior state of the art, and delivers a 22.8x speedup on average compared to a layer-by-layer
attention implementation on XDNA 2.
Read the full abstract ▾
All authors Victor J.B. Jung, Gagandeep Singh, Joseph Melber, Kristof Denolf, Francesco Conti, Luca Benini
Artificial Intelligence · Cross-listed from quant-ph
When Routes Run Out: Adversarial Co-Learning and Explainable Robustness in Quantum Repeater Networks
Brennan Bell, Inti Gabriel Mendoza Estrada, Andreas Trügler et al. (+1 more)
We study an
adversarial bandit problem for
entanglement-based
quantum-network routing over a modest graph corpus. Alice selects an end-to-end repeater route for an Ekert-91 protocol (E91) representing her move, while Eve selects an attack surface, either edge intercept–resend or repeater
memory degradation. Payoffs are drawn from cached SeQUeNCe-simulated E91 transcripts, and Alice accepts a turn when the finite-sample statistic violates the Clauser-Horne-Shimony-Holt (CHSH) bound. Performing
adversarial co-learning across 50 structured
topologies, we find that learned retention tracks a full-
matrix minimax reference closely (Pearson $r=0.99$): under a one-surface Eve action model, bottleneck families have zero retention, while non-bottleneck families follow a $1-1/N$ coverage principle. We then fit decision-tree explanation models to graph-, attack-, and route-level
topology-corpus targets and report their faithfulness. Finally, we construct
prompt records for local
language models to summarize the tree evidence, resulting in an open-source explanation workflow for
quantum-repeater network games.
Read the full abstract ▾
All authors Brennan Bell, Inti Gabriel Mendoza Estrada, Andreas Trügler, Paul Erker
Artificial Intelligence · Cross-listed from cs.SE
Diversifying to Verify: When Task-Equivalent Programs Differ in Verifiability
Shirley Yu and Ruben Martins
Program verification is crucial for software correctness, but producing fully verified programs remains difficult in practice. This paper studies whether implementation structure affects automated verifiability when multiple generated programs are intended to satisfy the same task-level semantics. We present Diversify2Verify, a staged LLM-based pipeline for Why3 that infers representation-specific contracts, generates and tests diverse recursive and imperative array/list implementations, and attempts verification with bounded verifier-guided annotation repair. We also construct a verification-oriented
benchmark of 73 tasks over integers, arrays, and lists, yielding 292 implementation variants. Diversify2Verify verifies 96 artifacts initially and 154 after two repair passes, improving artifact-level verification from 32.9% to 52.7%. At the task level, at least one variant verifies for 49 of 73 tasks, a 67.1% success rate. These results show that task-equivalent implementations can differ substantially in verifiability and that implementation diversity helps find verification-friendly artifacts.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
CtrlVTON: Controllable Virtual Try-On via Visual-Instance-Prompt Segmentation
Seungyong Lee, Hyun Jun Jang, Sangoh Kim et al. (+1 more)
Virtual try-on (VTO) has made significant progress in realistically transferring garments onto a target person. Yet most systems give the user little control over how a garment should be worn – its size (loose or fitted), style (e.g., tucked in or untucked, open or closed), and spatial placement on the body. We address this gap with two complementary contributions. First, we define and solve Visual-Instance-
Prompt Segmentation via VIP-SAM: given a flatlay image of a garment, segment that specific instance in a photograph of a person wearing it. This is an instance-level task, distinct from the typically studied category-level
segmentation. Second, we introduce CtrlVTON, a controllable VTO framework that recasts try-on as an image editing problem and adds
segmentation masks as pixel-level control over garment layout, including style, size, and spatial placement on the body. VIP-SAM and CtrlVTON each achieve state-of-the-art results on their respective tasks. In particular, CtrlVTON generates images that follow user-provided layouts far more faithfully than the strongest proprietary editing systems while matching them on garment fidelity.
Read the full abstract ▾
All authors Seungyong Lee, Hyun Jun Jang, Sangoh Kim, Sungjoon Park
Artificial Intelligence · Cross-listed from cs.CL
Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented Generation
Cedric Caruzzo, Donggeun Yoo and Tae Soo Kim
Retrieval-augmented generation evaluation checks whether model claims are factually grounded in retrieved documents. It does not check whether retrieved evidence is attributed to the correct entity. A clinical RAG response can pass every automated check (zero
hallucinations, near-perfect faithfulness, real citations) while presenting drug Y's clinical evidence as evidence about queried drug X. We term this deceptive grounding (DG): a failure invisible to faithfulness,
hallucination, and citation checks because every claim is sourced from a real document, about the wrong entity. Using a controlled factorial
benchmark across 13 models, we find DG rates spanning 8-87% at peak
adversarial conditions. Medical and biomedical fine-tuned models reach up to 86.7%; domain specialization amplifies the failure rather than mitigating it. A controlled ablation identifies the mechanism: removing entity-specific clinical evidence from retrieved documents eliminates entity-attribution failure entirely, shifting all failures to confabulation. The two failure modes respond to the same trigger, taking different paths. Production measurement across 740 drug-disease pairs finds 7.8% overall DG in a deployed RAG system, rising to 13.6% for recently approved drugs. Entity-attribution verification (checking that cited evidence applies to the queried entity) detects DG at 97.0% precision and 98.7% DG recall (IPW-adjusted human gold standard); no existing framework implements it.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Shortcut Trajectory Planning for Efficient Offline Reinforcement Learning
Guanquan Wang and Yoshimasa Tsuruoka
Diffusion-based trajectory planners have shown strong performance in offline reinforcement learning, but their iterative denoising process often incurs high inference cost. Consistency-based planners reduce the number of sampling steps, yet they typically rely on a two-stage teacher–student
distillation pipeline that increases training cost and may introduce instability. We propose Shortcut Trajectory Planning (STP), an offline model-based reinforcement learning framework that incorporates shortcut models as efficient trajectory generators. STP trains a conditional shortcut trajectory model in a single stage, supports adjustable one-step and few-step inference through step-size conditioning, and selects candidate plans using a critic augmented with feasibility-aware correction. Across standard D4RL
benchmarks, including locomotion,
navigation, manipulation, and dexterous control tasks, STP achieves strong performance while simplifying the training pipeline for fast generative planning.
Read the full abstract ▾
Artificial Intelligence
Communication-Efficient Digital-Twin Coordination for Heterogeneous LLM Embodied Agents over Computing Power Networks
Nuocheng Yang, Sihua Wang, Zihan Chen et al. (+2 more)
Embodied agent teams powered by heterogeneous large
language models (LLMs) are being widely deployed in physical artificial intelligence such as smart factories, warehouses, and service robotics. To enable collaboration among such an
agent team, efficient coordination mechanisms that operate reliably under limited network resources are required. However, existing heterogeneous LLM-
agent coordination frameworks that rely on multi-round natural-
language-based conversations introduce three coupled challenges. First, inter-
agent dialogue incurs communication overhead that grows rapidly with team size. Second, the quality of coordination is constrained by the heterogeneous capabilities of the
agent team's LLMs. Third,
agents may suffer from action delays due to iterative negotiation. To address these challenges, we propose LDT-Coord, a networked coordination framework built upon a lightweight digital twin (DT). Specifically, each
agent independently selects its intended action and reports both the action decision and a structured temporal constraint over shared resources to the DT server, thereby decoupling coordination performance from natural-
language reasoning ability. Then, DT executes a training-free, rule-based orchestrator
algorithm to resolve cross-
agent conflicts and returns coordination instructions to prevent such conflicts. To further reduce communication overhead, we formulate
agent reporting control as a constrained partially observable Markov decision process (C-POMDP) and solve it with the PPO-Lagrangian
algorithm. Simulation results show that LDT-Coord achieves a task success rate comparable to conventional coordination methods while reducing communication overhead by more than 70x and maintaining robustness under LLM heterogeneity.
Read the full abstract ▾
All authors Nuocheng Yang, Sihua Wang, Zihan Chen, Tony Q. S. Quek, Changchuan Yin