Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达,利用大语言模型自动生成交叉领域文献分析简报。

01.
arXiv (CS.CV) 2026-06-11

Benchmarking Cross-Domain Audio-Visual Deception Detection

Automated deception detection is crucial for assisting humans in accurately assessing truthfulness and identifying deceptive behavior. Conventional contact-based techniques, like polygraph devices, rely on physiological signals to determine the authenticity of an individual's statements. Nevertheless, recent developments in automated deception detection have demonstrated that multimodal features derived from both audio and video modalities may outperform human observers on publicly available datasets. Despite these positive findings, the generalizability of existing audio-visual deception detection approaches across different scenarios remains largely unexplored. To close this gap, we present the first cross-domain audio-visual deception detection benchmark, that enables us to assess how well these methods generalize for use in real-world scenarios. We used widely adopted audio and visual features and different architectures for benchmarking, comparing single-to-single and multi-to-single domain generalization performance. To further exploit the impacts using data from multiple source domains for training, we investigate three types of domain sampling strategies, including domain-simultaneous, domain-alternating, and domain-by-domain for multi-to-single domain generalization evaluation. We also propose an algorithm to enhance the generalization performance by maximizing the gradient inner products between modality encoders, named ``MM-IDGM". Furthermore, we proposed the Attention-Mixer fusion method to improve performance, and we believe that this new cross-domain benchmark will facilitate future research in audio-visual deception detection.

02.
arXiv (CS.CL) 2026-06-17

Structural Role Injection in Handlebars-Templated LLM Prompts: Triple-Brace Interpolation, Delimiter Family, and the Limits of HTML Auto-Escaping

Large language model applications build prompts from templates, and Handlebars is a widely used templating engine and the default prompt-template format in Microsoft Semantic Kernel. Its double-brace {{x}} expression HTML-escapes the interpolated value and is documented as the safe default; its triple-brace {{{x}}} expression inserts the value raw. We show that this choice silently governs an application's exposure to structural role injection, where attacker-controlled data carries chat role delimiters that forge a higher-privilege turn. A model-free analysis establishes the mechanism: Handlebars escaping rewrites angle brackets but not square brackets, colons, or Markdown hashes, so it neutralises ChatML, Llama-3, and XML role delimiters (survival rate 0.00) while leaving Llama-2 [INST], legacy Human:/Assistant:, and Markdown ### delimiters intact (survival rate 1.00 for the last two). We then run 5760 trials across seven delimiter families, two attack objectives, and four models (GPT-3.5 Turbo, GPT-4o mini, GPT-4.1 mini, Claude Haiku 4.5) at a combined API cost of 1.63 USD. GPT-3.5 Turbo follows the task-hijack instruction in 97% of raw and 91% of escaped trials, with the escaping protection concentrated in the angle-bracket families and absent for the colon- and Markdown-based families; the harder secret-exfiltration objective, which does not saturate, exposes the same family interaction more cleanly. Claude Haiku 4.5 resists both objectives almost entirely. The escaped default protects only the delimiter schemes whose characters HTML escaping happens to cover, gives no protection for the rest, and cannot substitute for a structural separation of instruction and data.

03.
arXiv (CS.CV) 2026-06-19

GenTrack2: An Improved Hybrid Approach for Multi-Object Tracking

This paper proposes a visual multi-object tracking method that jointly employs stochastic and deterministic mechanisms to ensure identifier consistency for unknown and time-varying target numbers under nonlinear dynamics. A stochastic particle filter addresses nonlinear dynamics and non-Gaussian noise, with support from particle swarm optimization (PSO) to guide particles toward state distribution modes and mitigate divergence through proposed fitness measures incorporating motion consistency, appearance similarity, and social-interaction cues with neighboring targets. Deterministic association further enforces identifier consistency via a proposed cost matrix incorporating spatial consistency between particles and current detections, detection confidences, and track penalties. Subsequently, a novel scheme is proposed for the smooth updating of target states while preserving their identities, particularly for weak tracks during interactions with other targets and prolonged occlusions. Moreover, velocity regression over past states provides trend-seed velocities, enhancing particle sampling and state updates. The proposed tracker is designed to operate flexibly for both pre-recorded videos and camera live streams, where future frames are unavailable. Experimental results confirm superior performance compared to state-of-the-art trackers. The source-code reference implementations of both the proposed method and compared-trackers are provided on GitHub: https://github.com/SDU-VelKoTek/GenTrack2

04.
medRxiv (Medicine) 2026-06-22

Anterior-superior hypothalamic enlargement as specific marker in episodic migraine: converging evidence from an independent discovery-replication design

Background: Growing evidence implicates the hypothalamus as a key structure in migraine pathophysiology; however, our understanding of its precise role and of the specific nuclei involved remains limited. We combined MRI data from our laboratory with publicly available MRI datasets from OpenNeuro to examine hypothalamic subunit volumes in episodic migraine and assess the specificity of these alterations relative to chronic pain conditions. Methods: Structural MRI combined with an automated atlas-based segmentation algorithm and a discovery-replication design was employed to investigate cross-sectional volumetric differences across 5 bilateral hypothalamic subunits in two independent migraine cohorts: DS1-MIG (DS1-MIG-base, n = 111 patients, n = 35 controls) and DS2-MIG (n = 27 patients, n = 31 controls). The adjusted volumes were compared between groups using MANOVA as an omnibus test, followed by Welch t-tests to test univariate follow-up. Longitudinal volumetric changes were additionally assessed in DS1-MIG participants with available follow-up scans using linear mixed models. To assess the specificity of findings to migraine, the same pipeline was applied to two chronic pain datasets, one including patients with fibromyalgia (DS-FM, n = 33 patients, n = 33 controls) and the other including patients with trigeminal neuralgia (n = 119 patients, n = 55 controls). Results: MANOVA revealed significant multivariate group differences in the discovery and replication migraine cohorts (DS1-MIG-base: = .006; DS2-MIG: = .008). Follow-up univariate analyses identified a consistent enlargement of the left anterior-superior subunit across both cohorts (FDR = .023 in DS1-MIG-base and FDR = .046 in DS2-MIG), representing the only cross-cohort replication finding. Beyond this shared signature, DS2-MIG exhibited additional significant enlargements of the right anterior-inferior and right tubular-inferior subunits. Longitudinal analyses in DS1-MIG showed that hypothalamic subunit volumes remained broadly stable over time within both migraine patients and control participants. No significant volumetric alterations were detected in the fibromyalgia or trigeminal neuralgia cohorts, either in multivariate or univariate analyses, underscoring migraine-specific findings. Conclusions: These findings provide evidence for subunit-specific hypothalamic structural alterations in migraine localized in the left anterior hypothalamic subunit. The stability of these differences over time and their absence in other chronic pain conditions suggest a migraine-specific structural organisation of hypothalamic circuitry.

05.
arXiv (CS.CV) 2026-06-24

ObsGraph: Hierarchical Observation Representation for Embodied Reasoning and Exploration

Embodied reasoning and exploration are increasingly considered crucial abilities for robots operating in complex and unfamiliar environments. To accomplish tasks in such settings, an agent must identify and acquire the information necessary for the task through exploration. We propose ObsGraph, an observation-centric hierarchical scene graph that unifies scene representation, retrieval, and exploration. It retains visual evidence and organizes it into room-view-object layers: rooms provide coarse semantic anchors, views preserve contextual object covisibility, and objects store fine-grained details. On top of this representation, we perform coarse-to-fine hierarchical retrieval under a bounded budget, and crucially use retrieval outcomes to structure the exploration candidate space–activating room-level exploration, view refinement, or frontier exploration–thereby tightly coupling representation, retrieval, and adaptive multi-scale exploration. Experiments across embodied reasoning and exploration benchmarks demonstrate improved success and efficiency, highlighting the benefits of structured scene representation and more targeted information gathering driven by identified evidence gaps.

06.
arXiv (CS.LG) 2026-06-11

Persistent Homology as a Theory of Emergent Structure

作者:

arXiv:2507.03065v2 Announce Type: replace Abstract: Why do some macroscopic structures remain identifiable even though their microscopic constituents continually change? Vortices persist while fluid parcels turn over, neural memories persist while spikes and synapses fluctuate, and institutions persist while individuals enter and leave. We propose a scale-relative answer: an emergent property is a persistent nontrivial homology class $[z]\in H_p=\ker\partial_p/\im\partial_{p+1}$, a macro-feature that is closed but not exact across a filtration of descriptions. This identification turns emergence into a measurement problem. Persistent bars detect stable macro-features, and we introduce a contractive-similarity (CS) graph operator to supply scaffold spectral gaps that predict robustness. Hodge decomposition separates harmonic macro-scaffold from exact and co-exact micro-flow; and functorial condensation explains when one level's emergent class becomes a unit for the next. The resulting scaffold-flow framework expresses six familiar signatures of emergence (i.e., inevitability, coherence, irreducibility, complementarity, robustness, and hierarchy) within one mathematical language. It also yields falsifiable predictions across atmospheric, neural, and social systems: genuine emergent structures should persist across filtrations, remain spectrally stable, respond disproportionately to harmonic interventions, and require timescale separation for hierarchical autonomy.

07.
arXiv (CS.CV) 2026-06-16

Variational Test-time Optimization for Diffusion Synchronization

Collaborative generation, which coordinates multiple diffusion trajectories to extend the capabilities of pretrained priors, has emerged as a powerful paradigm for extending the applicability of diffusion models. Among existing approaches, diffusion synchronization provides a scenario-agnostic solution by introducing general guidance mechanisms. However, current synchronization approaches rely heavily on heuristics and still require task-specific tailoring, which limits their generalizability and performance. In this work, we mathematically derive a synchronization framework based on optimal control, providing a principled explanation of diffusion synchronization. During sampling, we optimize control variables to guide multiple trajectories toward coherent solutions while remaining close to the underlying diffusion prior. Our method operates entirely at test-time without additional training, thereby enabling broad applicability across diverse generation scenarios when combined with strong pretrained priors. We demonstrate consistent improvements over baselines on three representative collaborative generation tasks, covering a wide range of modalities and applications. Beyond performance gains, our work establishes a novel foundation for collaborative generation, opening a principled path toward extending pretrained generative models to new collaborative generation settings.

08.
arXiv (CS.CV) 2026-06-16

HMR-Net: Hierarchical Modular Routing for Cross-Domain Object Detection in Aerial Images

Despite advances in object detection, aerial imagery remains a challenging domain, as models often fail to generalize across variations in spatial resolution, scene composition, and semantic label coverage. Differences in geographic context, sensor characteristics, and object distributions across datasets limit the capacity of conventional models to learn consistent and transferable representations. Shared methods trained on such data tend to impose a unified representation across fundamentally different domains, resulting in poor performance on region-specific content and less flexibility when dealing with novel object categories. To address this, we propose a novel modular learning framework that enables structured specialization in aerial detection. Our method introduces a hierarchical routing mechanism with two levels of modularity: a domain routing layer that uses latent geographic embeddings to assign inputs to domain-specialized expert modules, and a scene routing mechanism that allocates image subregions to scene-specific expert modules. This allows our method to specialize across datasets and within complex scenes. Additionally, the framework contains a conditional expert module that uses external semantic information (e.g., category names or textual descriptions) to enable detection of novel object categories during inference, without the need for retraining or fine-tuning. By moving beyond monolithic representations, our method provides an adaptive framework for remote sensing object detection. Comprehensive evaluations on four datasets highlight improvements in multi-dataset generalization, region-level specialization, and open-category detection.

09.
PLOS Medicine 2026-06-16

The data transparency crisis in research: Lessons from systematic reviews and meta-analyses

by Saul Martin-Rodriguez, Rodrigo Fernandez-Gonzalo, David Moher Summary points Systematic reviews and meta-analyses underpin clinical guidelines and health policy, yet their validity may be compromised by limited access to underlying datasets and associated analytical code. Reliance on incomplete or inconsistently reported summary statistics forces researchers to use imputation and unverifiable assumptions, which can distort effect estimates and mislead clinical decision-making. The consequences extend beyond methodology: flawed evidence synthesis can influence treatment recommendations, healthcare spending, and patient safety, as illustrated by historical cases such as hormone replacement therapy. Despite widespread data-sharing policies, compliance remains low, enforcement weak, and monitoring almost non-existent, with many datasets remaining unavailable or inaccessible. This Policy Forum argues for strengthening enforceable data-sharing mechanisms, including clearer enforcement and pragmatic verification approaches within editorial workflows.

10.
arXiv (CS.LG) 2026-06-16

Generative Molecular Design with Steerable and Granular Synthesizability Control

arXiv:2505.08774v2 Announce Type: replace-cross Abstract: Designing molecules that are both property-optimal and readily synthesizable is a central challenge in drug discovery. Existing works that do consider synthesizability can jointly output predicted synthesis routes for generated molecules. However, there has been minimal attention in addressing the ease of synthesis and with flexibility to incorporate desired reaction constraints. On the other hand, virtual screening searches for commercially available compounds, but imposes challenges when scaling to ultra-large (billion-size and beyond) chemical spaces. Here, we propose a generative design framework that unifies synthesis-constrained molecular design and ultra-large-scale virtual screening through steerable and granular synthesizability control. Generated molecules satisfy arbitrary multi-parameter optimization objectives with predicted synthesis routes satisfying mix-and-match constraints: including or avoiding certain reactions, incorporating specific building blocks, and minimizing synthesis route length. In an end-to-end in-house campaign targeting BRD4, we designed molecules synthesizable with specific selected reactions and building blocks, synthesized all six selected compounds, and identified two micromolar binders. We further demonstrate that reaction control enables efficient navigation of ultra-large make-on-demand chemical spaces to identify property-optimal candidates. By applying our framework to Chemspace's Freedom 4.0 make-on-demand space (142 billion molecules), we generated ~320k molecules (0.00023% of the library) on a single consumer-grade GPU (with only 8 GB GPU memory) and identified a micromolar Wee1 binder amongst 60 synthesized candidates. The single unified framework thus enables generating novel synthesizable molecules and retrieving catalogue-ready candidates, offering a flexible solution to mitigating the synthesizability bottleneck.

11.
bioRxiv (Bioinfo) 2026-06-11

HoloCell: A Generative Foundation Model for Holistic Cellular Modeling

Single-cell multi-omics technologies have recently advanced to enable the profiling of epigenomic, transcriptomic, and proteomic layers within individual cells, offering new opportunities to characterize cellular states as integrated biological systems. However, developing a unified framework that can seamlessly integrate diverse omics modalities and remain robust to heterogeneous modality missingness remains challenging. Here we present HoloCell, to our knowledge the first generative foundation model for joint representation learning and generative modeling across all three major single-cell omics modalities, i.e., epigenomics, transcriptomics, and proteomics. HoloCell contains over 860 million parameters and is pretrained on the Human-Multi-Omics-Corpus, which comprises approximately 468 million single-cell profiles across these three omics layers, corresponding to over 425 billion tokens. HoloCell introduces a simple yet biologically grounded hierarchical tokenization strategy that encodes cis-regulatory elements, genes, and proteins as structured tokens within a shared modeling framework. We evaluated HoloCell across single-omics representation learning, paired multi-omics integration, unpaired multi-omics alignment, and cross-modal generation via iterative diffusion and remasking, demonstrating its superior performance and flexibility across diverse omics tasks. From a representation perspective, HoloCell provides a unified digital mapping of cellular states across multiple omics layers, capturing cell heterogeneity as an integrated system. From a generation perspective, its iterative diffusion and remasking framework accounts for the inherently unordered nature of biological features, enabling in silico simulation of multi-omics information flow. Together, these capabilities position HoloCell as a versatile foundation model toward the emerging concept of a virtual cell, offering both systematic characterization and generative simulation of cellular systems within a unified framework.

12.
arXiv (CS.CL) 2026-06-18

ForecastBench-Sim: A Simulated-World Forecasting Benchmark

Forecasting benchmarks for general-purpose AI systems usually inherit the constraints of the real world: outcomes resolve slowly, tail events are rare, and counterfactual questions are difficult to score. We introduce ForecastBench-Sim, a simulated-world forecasting benchmark built on game rollouts from Freeciv, a turn-based strategy game modelled on the Civilization series. Forecasters receive a fixed world report (a structured snapshot of the current game state) and answer questions about hidden future states; the benchmark then continues the simulation and scores forecasts. Because the world is simulated, the same setup can generate continuous or binary forecasting questions at arbitrary time horizons, paired intervention worlds for conditional or causal questions, and resolved examples of rare or disruptive outcomes. We describe the benchmark pipeline, question families, scoring protocol, and release artifacts, and report validation slices from model evaluations and an anonymized human pilot. ForecastBench-Sim is intended to complement real-world forecasting benchmarks by providing controlled, immediately resolvable tasks for studying probabilistic reasoning under dynamic world states.

13.
Science (Express) 2026-05-06

A 481-meter-high landslide-tsunami in a cruise ship–frequented Alaska fjord | Science

作者: 未知作者

Early in the morning of 10 August 2025, a >64 × 10 6 m 3 landslide struck Tracy Arm fjord in Alaska. The landslide was preconditioned by glacial retreat caused by climate change. The resulting 481 m runup megatsunami followed an initial 100-m-high breaking wave traveling >70 m s −1 . The landslide was preceded by several days of microseismicity, which increased in rate and magnitude until ~1 hour before failure. The landslide produced globally observed long-period seismic waves equivalent in size to a M5.4 earthquake. A long-period (~66 s) global seismic signal, produced by a landslide-induced seiche trapped within the fjord, persisted for up to 36 hours, the second time a days-long seiche has been thus observed. With fjord regions increasingly visited by cruise ships, and climate change making similar events more likely, this unanticipated, near-miss event highlights the growing risk from landslides and tsunamis in coastal environments.

14.
arXiv (quant-ph) 2026-06-19

GPU-accelerated semidefinite programming for causal games

arXiv:2606.20519v1 Announce Type: new Abstract: The process matrix formalism describes quantum correlations in scenarios without a fixed causal order between local laboratories. Operational signatures of such correlations can be investigated through causal games. A paradigmatic example is the Guess-Your-Neighbour's-Input game, in which two parties attempt to guess each other's inputs. Correlations compatible with any definite, or probabilistically mixed, causal order cannot achieve a winning probability exceeding $1/2$. The best process-matrix strategy currently known attains a value of approximately $0.6218$ using local dimension $d=5$, while the strongest known dimension-independent upper bound is $0.7592$. In this work, we investigate whether increasing the local dimension beyond $d = 5$ can narrow this gap. To this end, we employ a see-saw optimization scheme in which each step is formulated as a semidefinite program. For scalability, we develop a custom implementation of the SCS solver in which the dominant computational cost, the projection onto the positive-semidefinite cone, is offloaded to a GPU, yielding a six-fold speedup. Using this implementation, we explore local dimensions up to $d = 8$, and we do not find significant improvements over the value at $d=5$. Our results suggest that either qualitatively different strategies are required to approach the known upper bound, or that the bound itself is not tight.

15.
arXiv (CS.CL) 2026-06-17

Self-Generated Error Training for Token Editing in Diffusion Language Models

作者:

Token-to-token (T2T) editing lets LLaDA2.1 revise committed tokens during block-diffusion decoding. The released recipe trains this editor on random vocabulary corruptions, but at inference the editor sees the model's own fluent, high-confidence draft errors instead. We study this training-inference mismatch and propose self-generated T2T, which performs a no-gradient draft pass, fills masked positions with predicted tokens, and supervises recovery in a second pass under these self-generated corruptions. We implement the update as a short LoRA continued-pretraining pass on LLaDA2.1-mini and evaluate on several benchmarks under the official Q-Mode T2T procedure with unchanged inference parameters. The method generally improves accuracy while reducing T2T edit intensity, mitigating failure modes such as final-digit transcription errors after otherwise correct reasoning and excessive self-correction before short factual answers.

16.
arXiv (CS.CV) 2026-06-16

Interpolation between Convolution and Attention via K-Nearest Neighbors

作者:

The shift from Convolutional Neural Networks to Transformers has reshaped computer vision, yet these two architectural families are typically viewed as fundamentally distinct. Convolutional Neural Networks are defined by spatially local convolution operations, while Transformers rely on global self-attention. We argue that convolution and self-attention, despite their apparent differences, can be unified within a single k-nearest neighbor aggregation framework. The critical insight is that both operations are special cases of neighbor selection and weighted aggregation. Convolution selects neighbors by spatial proximity while self-attention selects by feature similarity, revealing that they lie on a continuous spectrum rather than representing categorically different computations. We introduce Convolutional Nearest Neighbors (ConvNN), a unified framework that formalizes this connection. ConvNN exactly recovers standard and depthwise convolution by restricting neighbor selection to normalized spatial coordinates, and exactly recovers self-attention and its sparse variants, including KVT-attention, by replacing spatial proximity with scaled dot-product similarity. Beyond these special cases, ConvNN serves as a drop-in replacement for both convolution and attention layers, enabling systematic exploration of the intermediate spectrum between local and global aggregation through configurable similarity functions, neighbor selection strategies, positional encodings, and aggregation kernels.

17.
arXiv (CS.AI) 2026-06-16

A Definition of Good Explanations and the Challenges Explaining LLM Outputs

arXiv:2606.14838v1 Announce Type: new Abstract: How to define a good explanation is a long-standing philosophical debate which has found recent renewed interest in the context of AI outputs. Explainability is crucial for AI adoption in many contexts, but in order to produce good explanations of AI systems, we must first have an understanding of what good explanations are. In this paper we propose a definition inspired by the notion of counterfactual explanations, however we argue that one must also take into account the interlocutor's prior beliefs in each fact that could be offered in an explanation. We explore the ramifications of this definition for AI explainability and, in particular, why LLM outputs are difficult to produce good explanations for.

18.
arXiv (CS.CV) 2026-06-11

Understanding Cross-Sensor Feature Variations for Generalizable 3D Perception

Radar-camera BEV perception often suffers from degraded performance when evaluated across datasets, as changes in driving scenes, sensor configurations, and environmental conditions can alter both the input observations and the internal fused representations. This work studies this issue from the perspective of source-domain variation modeling, aiming to improve the robustness of BEV-based 3D detectors without relying on target-domain samples. We introduce a framework that characterizes visual scene variations in the frequency domain and uses them to synthesize diverse source-domain views. By comparing the resulting fused BEV representations, the framework further captures how image-level variations influence multi-modal BEV features. These variation patterns are then used to regularize the detector, encouraging the learned fusion space to remain stable under latent scene changes. The proposed method is applied only during training and leaves the inference pipeline unchanged. Experiments on cross-dataset radar-camera 3D detection between View-of-Delft and TJ4DRadSet demonstrate consistent improvements over multiple BEV fusion backbones, and the gains remain effective when a small amount of target-domain data is available.

19.
arXiv (CS.CL) 2026-06-19

Efficiently Representing Algorithms With Chain-of-Thought Transformers

The increasing popularity of reasoning models – language models that output a series of reasoning or thought tokens before producing an answer – is justified, in part, by theoretical results showing that chain-of-thought (CoT) transformers can simulate Turing machines, and thus perform arbitrary computation. However, the Turing machine, while suitable for complexity-theoretic analysis, is not convenient, intuitive, or efficient for discussing algorithms. Algorithms are typically designed and analyzed at a higher level of abstraction, captured by the Word RAM model with random-access memory and unit-cost operations on $\bigO(\log n)$-bit words. As a result, Word RAM algorithms can be substantially more efficient than their Turing machine counterparts, raising the question: Can CoT transformers efficiently simulate Word RAM algorithms? For instance, can they sort $n$ items in $\bigO(n \log n)$ steps or run Dijkstra's algorithm in $\bigO(E + V \log V)$ steps? We answer affirmatively, up to poly-logarithmic overhead. We first establish this for finite-precision transformers with poly-logarithmic width and rightmost unique hard attention, then strengthen the result to two more practical settings with finite width and log-precision: continuous CoT, where reasoning takes the form of vectors rather than tokens, and a hybrid architecture in which transformer layers sit atop a recurrent (linear RNN) layer. In all three cases, we find that CoT can efficiently simulate any Word RAM algorithm with only a poly-logarithmic overhead in $n$. This overhead reduces to log-square when the Word RAM has a ``flat'' instruction set, and only logarithmic for multiplication-free flat instructions – in stark contrast to known CoT simulations of Turing machines, which require quadratic overhead over Word RAM.

20.
arXiv (CS.LG) 2026-06-17

Instrumental and Proximal Causal Inference with Gaussian Processes

arXiv:2603.02159v2 Announce Type: replace-cross Abstract: Instrumental variable (IV) and proximal causal learning (Proxy) methods are central frameworks for causal inference in the presence of unobserved confounding. Despite substantial methodological advances, existing approaches rarely provide reliable epistemic uncertainty (EU) quantification. We address this gap through a Deconditional Gaussian Process (DGP) framework for uncertainty-aware causal learning. Our formulation recovers popular kernel estimators as the posterior mean, ensuring predictive precision, while the posterior variance yields principled and well-calibrated EU. Moreover, the probabilistic structure enables systematic model selection via marginal log-likelihood optimization. Empirical results demonstrate strong predictive performance alongside informative EU quantification, evaluated via empirical coverage frequencies and decision-aware accuracy rejection curves. Together, our approach provides a unified, practical solution for causal inference under unobserved confounding with reliable uncertainty.

21.
arXiv (CS.LG) 2026-06-19

Tracking Representation Dynamics in Large Language Models with Persistent Homology

arXiv:2606.19542v1 Announce Type: new Abstract: Large language models are commonly aligned through supervised fine-tuning, yet little is known about how their internal representations evolve during this process. We study alignment dynamics using persistent homology by tracking the topology of activation spaces throughout fine-tuning. Across four transformer language models ranging from 1B to 7B parameters and three alignment objectives corresponding to helpful, harmless, and mixed training data, we find that the majority of topological reorganization occurs during the earliest stages of training. A dense checkpoint analysis reveals a transient peak in topological activity followed by rapid stabilization. We further show that different alignment objectives induce distinguishable topological trajectories, while instruction-tuned and pretrained models exhibit qualitatively different patterns of evolution. Our results suggest that persistent homology provides a complementary perspective on alignment, revealing representation-level changes that are not apparent from behavioral metrics alone.

22.
arXiv (CS.LG) 2026-06-17

Uncertainty Quantification for Flow-Based Vision-Language-Action Models

arXiv:2606.18043v1 Announce Type: cross Abstract: Vision-language-action models (VLAs) combine vision-language backbones with expressive generative action heads trained via flow matching on large-scale robotic datasets. Despite their strong empirical performance in robotic manipulation, VLAs lack mechanisms to quantify confidence in their predictions and to detect when their actions may be unreliable. This presents a critical limitation for real-world deployment in non-stationary environments, where models inevitably encounter scenarios outside their pretraining distribution and may fail without warning. To address this, we derive an efficient method for quantifying epistemic uncertainty in flow-matching models by leveraging velocity-field disagreement (VFD) across a small ensemble. We successfully use this uncertainty estimate for failure detection during deployment and active fine-tuning of flow-based VLAs. To this end, we propose SAVE, a framework for uncertainty-guided active multitask fine-tuning that reduces the number of costly expert demonstrations required to adapt VLAs to new tasks. Through extensive experiments on the LIBERO benchmark, we demonstrate that VFD yields better-calibrated uncertainty estimates predictive of downstream performance, that VFD achieves strong performance in detecting failures, and that uncertainty-guided data acquisition with SAVE requires at least 22% fewer samples than baselines. In summary, our work shows that quantifying epistemic uncertainty in flow-based VLAs improves both failure awareness and adaptation. Project website: tum-lsy.github.io/uq_vla/.

23.
arXiv (CS.AI) 2026-06-24

Skills for the future software profession: beyond agentic AI!

arXiv:2606.21894v2 Announce Type: replace-cross Abstract: As coding agents are rapidly changing software engineering, a natural question is: what are the core skills needed by future software engineers? To identify where software engineering is headed and thus what skills will be needed, we summarize the results of two round-tables with researchers and industrial practitioners, held in 2026 in New York and Singapore. One key finding is that verification and validation is increasing in importance as agents handle implementation, as highlighted by anecdotes from the events. From our observations, we identify the skills developers need in the agentic era of development, with implications for training and educating future software engineers in coming years.

24.
arXiv (CS.LG) 2026-06-16

Photon: Federated LLM Pre-Training

arXiv:2411.02908v2 Announce Type: replace Abstract: Scaling large language models (LLMs) demands extensive data and computing resources, which are traditionally constrained to data centers by the high-bandwidth requirements of distributed training. Low-bandwidth methods like federated learning (FL) could enable collaborative training of larger models across weakly-connected GPUs if they can effectively be used for pre-training. To achieve this, we introduce Photon, the first complete system for federated end-to-end LLM training, leveraging cross-silo FL for global-scale training with minimal communication overheads. Using Photon, we train the first federated family of decoder-only LLMs from scratch. We show that: (1) Photon can train model sizes up to 7B in a federated fashion while reaching an even better perplexity than centralized pre-training; (2) Photon model training time decreases with available compute, achieving a similar compute-time trade-off to centralized; and (3) Photon outperforms the wall-time of baseline distributed training methods by 35% via communicating 64x-512xless. Our proposal is robust to data heterogeneity and converges twice as fast as previous methods like DiLoCo. This surprising data efficiency stems from a unique approach combining small client batch sizes with extremely high learning rates, enabled by federated averaging's robustness to hyperparameters. Photon thus represents the first economical system for global internet-wide LLM pre-training.

25.
arXiv (CS.AI) 2026-06-15

PRISM: Perception Reasoning Interleaved for Sequential Decision Making

arXiv:2605.05407v2 Announce Type: replace Abstract: Scaling LLM-based embodied agents from text-only environments to complex multimodal settings remains a major challenge. Recent work identifies a perception-reasoning-decision gap in standalone Vision-Language Models (VLMs), which often overlook task-critical information. In this paper, we introduce PRISM, a framework that tightly couples perception (VLM) and decision (LLM) through a dynamic question-answer (DQA) pipeline. Instead of passively accepting the VLM's description, the LLM critiques it, probes the VLM with goal-oriented questions, and synthesizes a compact image description. This closed-loop interaction yields a sharp, task-driven understanding of the scene. We evaluate PRISM on the ALFWorld and Room-to-Room (R2R) benchmarks. We show that: (1) PRISM significantly outperforms state-of-the-art image-based models, (2) our Interactive goal-oriented perception pipeline yields systematic and substantial gains, and (3) PRISM is fully automatic, eliminating the need for handcrafted questions or answers.