×

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。

作者: Thomas Li ×
换一批
01.
arXiv (quant-ph) 2026-06-16

Complete entanglement detection using polynomial invariants

arXiv:2606.16712v1 Announce Type: new Abstract: Existing methods for deciding whether a bipartite quantum state is separable or entangled typically fall into one of two categories: they are either complete but require access to an explicit density matrix followed by numerical optimization, or they can be evaluated directly by measuring the quantum system but are incomplete, in the sense that they cannot detect all forms of entanglement. In this work, we overcome both limitations in a unified framework. First, we bypass numerical optimization by deriving separability criteria in the form of universal bounds on tensor powers of separable states. We prove that these bounds are complete: every entangled state violates them for sufficiently large tensor powers. Second, we explicitly construct a corresponding complete family of nonlinear entanglement witnesses, which can detect all forms of entanglement without requiring an explicit density matrix. The witnesses we construct are moreover basis-independent, in the sense that they are invariant under conjugation by local unitaries. Altogether, our results expand the toolbox for entanglement detection in arbitrary local dimensions in a manifestly invariant way.

02.
arXiv (CS.CV) 2026-06-11

MentisOculi: Revealing the Limits of Reasoning with Mental Imagery

Frontier models are transitioning from multimodal large language models (MLLMs) that merely ingest visual information to unified multimodal models (UMMs) capable of native interleaved generation. This shift has sparked interest in using intermediate visualizations as a reasoning aid, akin to human mental imagery. Central to this idea is the ability to form, maintain, and manipulate visual representations in a goal-oriented manner. To evaluate and probe this capability, we develop MentisOculi, a procedural, stratified suite of multi-step reasoning problems amenable to visual solution, tuned to challenge frontier models. Evaluating visual strategies ranging from latent tokens to explicit generated imagery, we find they generally fail to improve performance. Analysis of UMMs specifically exposes a critical limitation: While they possess the textual reasoning capacity to solve a task and can sometimes generate correct visuals, they suffer from compounding generation errors and fail to leverage even ground-truth visualizations. Our findings suggest that despite their inherent appeal, visual thoughts do not yet benefit model reasoning. MentisOculi establishes the necessary foundation to analyze and close this gap across diverse model families.

03.
arXiv (CS.CV) 2026-06-11

How Seemingly Inconsequential Design Choices Dictate Performance of LLMs in Pathology

General-purpose large language models (LLMs) are routinely used as baselines when evaluating specialized pathology models on whole-slide images (WSIs). Because WSIs exceed contemporary model context limits, LLM baselines routinely use small, high-magnification patches processed independently via majority voting, without systematic evaluation of seemingly inconsequential design choices such as patch size, patch count, and magnification. Generalist LLMs have consistently underperformed specialized systems, reinforcing the perception that domain-specific training or architectural adaptation is necessary for pathology tasks involving WSIs. Here, we conduct a systematic factorial analysis of four input design factors: inference mode, patch size, magnification, and patch count. We demonstrate that prior studies have overstated the gap between specialized models and general-purpose LLMs by choosing non-optimized input configurations. On the MultiPathQA benchmark, switching to a single balanced configuration (large patches at lower magnification, processed jointly) raises GPT-5 from 15.1% to 39.5% on cancer-type classification (TCGA) and from 38.1% to 62.9% on organ classification (GTEx). Per-task optimization yields further gains up to 43.9% (TCGA) and 71.6% (GTEx). The same configuration generalizes to two other models and to a fully held-out CPTAC cohort, where it improves Gemini 3 Flash by 23.4 percentage points without any task-specific tuning.

04.
arXiv (CS.AI) 2026-06-19

DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis

arXiv:2604.13416v2 Announce Type: replace-cross Abstract: Advances in radiance fields have enabled photorealistic novel view synthesis. In several domains, large-scale real-world datasets have been developed to support comprehensive benchmarking and to facilitate progress beyond scene-specific reconstruction. However, for distractor-free radiance fields, a large-scale dataset with clean and cluttered images per scene remains lacking, limiting the development. To address this gap, we introduce DF3DV-1K, a large-scale real-world dataset comprising 1,048 scenes, each providing clean and cluttered image sets for benchmarking. In total, the dataset contains 89,924 images captured using consumer cameras to mimic casual capture, spanning 128 distractor types and 161 scene themes across indoor and outdoor environments. A curated subset of 41 scenes, DF3DV-41, is systematically designed to evaluate the robustness of distractor-free radiance field methods under challenging scenarios. Using DF3DV-1K, we benchmark nine recent distractor-free radiance field methods and 3D Gaussian Splatting, identifying the most robust methods and the most challenging scenarios. Beyond benchmarking, we demonstrate an application of DF3DV-1K by fine-tuning a diffusion-based 2D enhancer to improve radiance field methods, achieving average improvements of 0.96 dB PSNR and 0.057 LPIPS on the held-out set (e.g., DF3DV-41) and the On-the-go dataset. We hope DF3DV-1K facilitates the development of distractor-free vision and promotes progress beyond scene-specific approaches. The dataset and leaderboard are available at https://johnnylu305.github.io/df3dv1k_web/.

05.
arXiv (CS.CV) 2026-06-12

SPARC: Reliable Spatial Annotations from Robot Demonstrations at Scale

This work introduces Spatial Annotations from Robot Demonstrations with Reliability Calibration (SPARC), a risk-aware framework that automatically labels robot demonstrations with structured spatial annotations and assigns each annotation a reliability score. Structured spatial annotations, such as bounding boxes, object trajectories, and manipulation phase labels, benefit a broad range of robotics applications from training grounded robot policies and embodied foundation models to motion planning and hierarchical task composition. Existing automated pipelines generate such annotations at scale but provide no reliable quality signal: detector confidence is poorly calibrated for annotation correctness, forcing a choice between accepting noisy labels or discarding useful samples. In contrast to existing automated pipelines, SPARC leverages the spatio-temporal structure inherent to robot tasks to generate a reliability signal, reducing noisy labels and retaining more useful samples. We further introduce Interaction-Aware Bench (IA-Bench), a benchmark that measures model accuracy in grounding the locations of interacted objects in robot demonstrations. On 1.7k human-annotated demonstrations spanning diverse embodiments and scenarios, SPARC significantly outperforms detection-only baselines in localization accuracy while retaining three times more samples at high-precision operating points. Our experiments demonstrate that models finetuned on our annotations achieve state-of-the-art results on object-grounding and pointing benchmarks among similarly sized models, while remaining competitive on broader spatial-reasoning suites without manually verified or annotated training data. Furthermore, policies trained on SPARC-generated annotations outperform baselines in cluttered, visually ambiguous real-world scenes. Code, data, and models are available at intuitive-robots.github.io/sparc-labeling.

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

Counterexample Guided Learning in the Large using Reasoning Agents

arXiv:2606.11521v1 Announce Type: new Abstract: LLMs and LLM agents should improve when given feedback, but identifying when they are able to do so is difficult: feedback is heterogeneous, domain-specific, and difficult to control. We approach this challenge by asking LLMs to perform regular-expression induction, a classical symbolic learning problem where precise mechanisms for feedback exist in the form of counterexamples. In counterexample-guided learning, a learner (LLM) proposes candidate regular expressions from positive/negative-labeled strings, and the teacher (verifier) returns counterexamples showcasing the difference between the candidate and target languages. We identify novel counterexample-guided refinement strategies that enable effective regex learning, such as regularization and symbolic counterexample clusters. We also explore agentic strategies such as reflection and repair loops. Empirically, we find that verifier feedback substantially improves sample efficiency on challenging regex-induction tasks, reducing the number of labeled examples required and enabling learning of complex target expressions where standard prompting fails. For example, on the hardest task groups, our counterexample-guided framework improves success from 3.2% to 38.1% and from 38.9% to 74.1% on two different regex domains. These results suggest that LLMs can benefit from rich feedback beyond treating it as additional data, opening the door for robust verifier-guided methods for LLM-based program synthesis and formal reasoning.

07.
arXiv (CS.CV) 2026-06-18

Cosmos 3: Omnimodal World Models for Physical AI

We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-transformers architecture. By supporting highly flexible input-output configurations, Cosmos 3 seamlessly unifies critical modalities for Physical AI – effectively subsuming vision-language models, video generators, world simulators, and world-action models into a single framework. Our evaluation demonstrates that Cosmos 3 establishes a new state-of-the-art across a diverse suite of understanding and generation tasks, demonstrating omnimodal world models as scalable, general-purpose backbones for embodied agents. Our post-trained Cosmos 3 models were ranked as the best open-source Text-to-Image and Image-to-Video models by Artificial Analysis, and the best policy model by RoboArena at the time the technical report was written. To accelerate open research and deployment in Physical AI, we make our code, model checkpoints, curated synthetic datasets, and evaluation benchmark available under the Linux Foundation's OpenMDW-1.1 License at https://github.com/nvidia/cosmos and https://huggingface.co/collections/nvidia/cosmos3. The project website is available at https://research.nvidia.com/labs/cosmos-lab/cosmos3.

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

The Perils of Agency: How Developers Perceive, Prioritize, and Address Risks in Agentic AI Products

arXiv:2606.15485v1 Announce Type: cross Abstract: Agentic AI systems act autonomously, use tools, adapt to context, and operate in complex real-world environments. However, these same characteristics can create or exacerbate product risks. We studied how industry developers (n=35) perceive, prioritize, and address the risks in their agentic AI products. We found that developers' perceptions of risk were closely tied to the qualities that made the product agentic, such as autonomy, tool use, and usage in a real-world context. Developers prioritized product and business risks before considering downstream societal risks like job displacement and end-user privacy. This prioritization also impacted developers' ability and motivation to mitigate agentic risks. Finally, developers lacked mature controls for containing agentic risks, often relying on constraining the same characteristics that make agents useful: e.g., autonomy and goal complexity. These findings reveal a capability vs. risk control tension in agentic AI development: developers need to address risks that emerge from agentic capabilities, yet they currently have limited support for doing so without constraining agentic functionality.

09.
arXiv (CS.AI) 2026-06-16

FlowState: Sampling-Rate-Equivariant Time-Series Forecasting

arXiv:2508.05287v3 Announce Type: replace-cross Abstract: Existing time series foundation models (TSFMs), often based on transformer variants, lack adaptability to different sampling rates, struggle with generalization across varying context and target lengths, and are computationally inefficient. We introduce FlowState, a novel TSFM architecture that achieves sampling-rate-equivariant forecasting through a unified design that pairs a state space model (SSM) encoder with a functional basis decoder (FBD). This design enables continuous-time modeling and dynamic time-scale adjustment, allowing FlowState to inherently generalize across all possible temporal resolutions, and dynamically adjust the forecasting horizons without retraining. We further propose an efficient pretraining strategy that improves robustness and accelerates training. Despite being one of the smallest TSFMs, FlowState achieves state-of-the-art results on the widely used GIFT-Eval benchmark, while demonstrating superior adaptability to unseen sampling rates. Our detailed analyses confirm the effectiveness of its components, and we demonstrate its unique ability to adapt to varying input sampling rates.

10.
arXiv (CS.AI) 2026-06-19

Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM Agents

arXiv:2606.19704v1 Announce Type: new Abstract: Agent benchmarks are growing fast, but no single benchmark touches more than four or five of the dimensions that deployment exposes. This paper aggregates the largest coordinated deep-dive of one MCP-based industrial-agent benchmark to date: fourteen parallel implementation studies covering new asset classes (including a multi-modal visual extension), alternative orchestrations, retrieval strategies, reasoning modes, infrastructure optimizations, and evaluation-methodology probes. Consolidating those studies with seven prior agent benchmarks, we argue that aggregate-score leaderboards systematically underspecify deployed-agent evaluation. Rankings derived from aggregate scores do not transfer to out-of-distribution settings; recent public-to-hidden competition retrospectives provide direct empirical evidence of this rank instability. We propose ranking configurations by predictive validity, the correlation between in-sample and out-of-sample rank, rather than in-sample mean, and report a twelve-tier measurement apparatus that exposes the deployment-relevant dimensions HELM and its agent-era successors collapse. The position is operationalized through three falsifiable out-of-distribution criteria with explicit thresholds; existing evidence partly supports it but is too thin to confirm. We close with a pre-registered pilot design and a field-level vision for what the next generation of agentic benchmarks should report.

11.
arXiv (CS.CL) 2026-06-12

RAGPPI: RAG Benchmark for Protein-Protein Interactions in Drug Discovery

Retrieving the biological impacts of protein-protein interactions (PPIs) is essential for target identification (Target ID) in drug development. Given the vast number of proteins involved, this process remains time-consuming and challenging. Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) frameworks have supported Target ID; however, no benchmark currently exists for identifying the biological impacts of PPIs. To bridge this gap, we introduce the RAG Benchmark for PPIs (RAGPPI), a factual question-answer benchmark of 4,420 question-answer pairs that focus on the potential biological impacts of PPIs. Through interviews with experts, we identified criteria for a benchmark dataset, such as a type of QA and source. We built a gold-standard dataset (500 QA pairs) through expert-driven data annotation. We developed an ensemble auto-evaluation LLM that incorporates expert labeling characteristics, average fact-abstract similarity (F1), and low-similarity fact counts (F2), enabling the construction of a silver-standard dataset (3,720 QA pairs). We are committed to maintaining RAGPPI as a resource to support the research community in advancing RAG systems for drug discovery QA solutions.

12.
arXiv (CS.AI) 2026-06-19

VCG: A Multimodal Retrieval Framework for E-Commerce Video Feeds under Extreme Cold-Start Conditions

arXiv:2606.19627v1 Announce Type: cross Abstract: The digital commerce landscape is shifting from static, search-driven catalogs to dynamic, immersive video feeds. This transition introduces an ``extreme cold-start'' problem: unlike traditional items, new short-form videos lack the dense interaction history required for collaborative filtering. Furthermore, immersive feeds introduce strong position and duration biases that distort standard engagement signals. In this paper, we demonstrate the Video Candidate Generation (VCG) system, a scalable multimodal retrieval engine designed to solve these challenges in a large-scale e-commerce environment. By leveraging a domain-adapted vision-language model (based on CLIP), we map users and videos into a shared semantic space, enabling zero-shot retrieval based on visual content rather than behavioral history. We detail the system's architecture and present a rigorous evaluation comparing generative (LLM) vs. discriminative (CLIP) embeddings. Our results show that while generative models excel at attribute prediction, they suffer from embedding space collapse in retrieval tasks. Online A/B testing demonstrates that VCG effectively mitigates engagement biases, yielding a 50\% uplift in deep video completion. To showcase the system's capabilities, we present an interactive demonstration featuring three bi-directional retrieval scenarios: Product-to-Video, Video-to-Product, and Zero-Shot Semantic Search.

13.
arXiv (CS.CL) 2026-06-15

The Culture Funnel: You Can't Align What isn't in the Data

Current cultural alignment approaches focus on inference-time interventions, assuming models already contain sufficient cultural knowledge. We argue modern LLM pipelines suffer from a cultural data funnel. Using a multidimensional tagging framework across pretraining, fine-tuning, alignment, and reasoning datasets, we show explicit cultural signals decline sharply during post-training, while geographically concentrated, task-specialized data dominates. Multilinguality enhances geographic diversity of cultural knowledge but does not ensure balanced representation. Our tags improve downstream cultural benchmark performance, demonstrating that advances require shifting focus in training data pipelines. To facilitate future research, we release our culturally tagged dataset with 5.6M samples at https://huggingface.co/datasets/CohereLabs/CultureMarkers.

14.
arXiv (CS.AI) 2026-06-19

Latent Gaussian Splatting for 4D Panoptic Occupancy Tracking

arXiv:2602.23172v2 Announce Type: replace-cross Abstract: Capturing 4D spatiotemporal scene structure is crucial for the safe and reliable operation of robots in dynamic environments. However, existing approaches typically address only part of the problem: they either provide coarse geometric tracking via bounding boxes or detailed 3D occupancy estimates that lack explicit temporal association and instance-level reasoning. In this work, we present Latent Gaussian Splatting (LaGS) for 4D Panoptic Occupancy Tracking (4D-POT). We revisit the underlying representation and model 3D features as a sparse set of feature-bearing Gaussians. These act as dynamic, volume-oriented keypoints that enable spatially continuous, distance-weighted aggregation of multi-view features before being splatted into a voxel grid for decoding. This point-centric formulation enables flexible, data-dependent receptive fields and long-range spatial interactions that are difficult to capture with local and dense voxel-based operators. A hierarchical Gaussian representation further enables multi-scale reasoning by combining global context from coarse super-points with fine-grained detail from higher-resolution streams. Extensive experiments on Occ3D nuScenes and Waymo demonstrate state-of-the-art performance for 4D-POT. We provide code and models at https://lags.cs.uni-freiburg.de/.

15.
arXiv (CS.AI) 2026-06-16

Task-guided cross-subject latent alignment: a multi-encoder-decoder VAE

arXiv:2606.15989v1 Announce Type: cross Abstract: Aligning neural activity across subjects offers the promise of discovering shared computational principles and generalizable decoders. However, traditional alignment methods require shared stimuli across subjects, a constraint that limits applicability to naturalistic paradigms with limited or non-overlapping data. We introduce a Multi-Encoder-Decoder Variational Autoencoder (MED-VAE) that achieves cross-subject alignment without shared stimuli by anchoring representations to a common scaffold provided by a pretrained ANN. Using the Natural Scenes Dataset, we show that MED-VAE creates common latent spaces with superior semantic organisation, achieving higher cross-subject alignment than common methods while maintaining robust generalisation to held-out stimuli where traditional methods degrade. Reconstructing from these common spaces back to each subject's original neural space, MED-VAE preserves equal stimulus-driven signal in its cross-subject latent space. Finally, we show that this superior alignment directly enables cross-subject neural prediction, as demonstrated via cross-subject image decoding. In summary, we introduce a framework to identify generalisable common subspaces for cross-subject predictions and downstream tasks, demonstrated here for visual cortex responses to static images.

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

Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers

arXiv:2606.18206v1 Announce Type: new Abstract: Looped architectures provide an inductive bias toward learning step-by-step procedures for tasks that require compositional reasoning. The number of effective layers reached by looping determines the quality of the solution these models find. Like deep architectures, looped architectures are prone to a signal propagation problem induced by depth as the halting decision is postponed. In this paper, we address this signal propagation issue using pre-norm layers and residual scaling. Building on these architectural modifications, we propose FPRM, a Transformer-based Fixed-Point Reasoning Model that uses fixed-point convergence as an end-to-end halting mechanism in a looped architecture. We show that fixed-point halting allows FPRM to adapt its compute to task difficulty. FPRM is effective on common reasoning benchmarks, namely Sudoku, Maze, state-tracking, and ARC-AGI.

17.
arXiv (math.PR) 2026-06-16

On stability of outliers from the circular law

arXiv:2606.16609v1 Announce Type: new Abstract: This work investigates the stability of outliers from the circular law, via the convergence of their associated diagonal overlaps between eigenvectors - also known as the squared eigenvalue condition numbers. We consider and compare two paradigmatic cases, namely: 1) the Complex Ginibre Ensemble conditioned on the existence of an outlier, and 2) the outlier induced by a rank-one Hermitian perturbation of a Complex Ginibre matrix. In both cases, we prove almost sure convergence towards a specific constant that only depends on the radius of the outlier and its status - either conditioned or induced. These results can be generalized to other complex integrable ensembles with the same techniques, and complement our understanding of eigenvalue stability in non-Hermitian ensembles.

18.
arXiv (CS.LG) 2026-06-19

FloatDoor: Platform-Triggered Backdoors in LLMs

arXiv:2606.19535v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in sensitive settings such as software engineering, where their outputs directly shape downstream artifacts. Recent work has shown that an identical model can produce measurably different outputs depending on the deployment platform, a consequence of non-associative floating-point arithmetic and divergent kernel implementations. We study the security implications of this platform-dependent variability and uncover a novel attack surface on LLM deployments. We introduce FloatDoor, the first input-independent, platform-triggered backdoor attack against generative LLMs. The compromised model exhibits adversary-chosen behavior when served on a target platform and is otherwise benign. FloatDoor is realized through two lightweight LoRA adapters, one that amplifies inter-platform numerical divergence and one that binds the resulting platform signature to a malicious downstream task, while leaving aggregate model utility largely intact. FloatDoor exploits a pronounced time-of-check, time-of-use gap between model auditing and serving. We demonstrate FloatDoor on Qwen3-4B across a broad range of deployment targets, including NVIDIA GPUs, Google TPUs, AWS Graviton, and Alibaba Yitian-710. As a final case study, we show that FloatDoor reliably induces exploitable code vulnerabilities on a chosen target platform. Our results establish a new class of attacks on LLM deployments and underscore the pressing need for trusted model supply chains in sensitive, LLM-powered applications.

19.
arXiv (CS.CV) 2026-06-16

GeoRoPE: Ground-Aware Rotary Adaptation for Remote Sensing Foundation Models

Remote-sensing foundation models (RSFMs) benefit from pretraining on imagery from multiple sensors and ground sampling distances (GSDs), but such exposure alone does not resolve scale mismatch during downstream adaptation. A fixed token-grid offset can correspond to different ground distances across sensors, making grid-based positional priors physically inconsistent. Meanwhile, heterogeneous spatial granularity means that compact urban regions and homogeneous landscapes may require different positional sensitivities even under the same GSD. Therefore, we propose {GeoRoPE}, a ground-aware, RoPE-compatible, and parameter-efficient spatial adaptation method for RSFMs. GeoRoPE recalibrates token-level positional interactions from two complementary aspects. First, Geo-Coordinate Calibration (GCC) rescales raw token-grid offsets according to the ground distance represented by one token-grid step, producing geo-calibrated relative coordinates across GSDs. Second, Geo-Frequency Calibration (GFC) adjusts the native RoPE frequency with a relation-specific factor, enabling position sensitive adaptation to scene-dependent spatial granularity. GeoRoPE is injected into pretrained RSFMs through a lightweight adapter, preserving the frozen spatial prior while adding geo-aware positional corrections. Experiments across multiple RSFMs, sensors, resolutions, and downstream tasks demonstrate that GeoRoPE improves cross-resolution robustness and scale-sensitive representation learning.

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

First, do NOHARM: towards clinically safe large language models

arXiv:2512.01241v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are routinely used by physicians and patients for medical advice, yet their clinical safety profiles remain poorly characterized. We present NOHARM (Numerous Options Harm Assessment for Risk in Medicine), a 1,100-task benchmark of primary care-to-specialist consultation cases to measure the frequency and severity of harm from LLM-generated medical recommendations. NOHARM covers 10 specialties, with 12,747 expert annotations for 4,249 clinical management options. Across 28 LLMs, recommendations carried the potential for severe harm in up to 22.6% of cases, with errors of omission accounting for more than 80% of severe errors. In a randomized trial of 101 generalist physicians, human benchmark performance significantly improved with AI assistance, yet physicians remained far from realizing the potential of AI tools, frequently ignoring essential advice surfaced by AI. Safety performance tracked general-intelligence and medical-knowledge benchmarks across the full range of models but decoupled at the frontier. Despite strong performance on existing evaluations, widely used AI models can produce medical advice with the potential for severe harm at non-trivial rates, highlighting the importance of explicit measurement of clinical safety.

21.
arXiv (CS.LG) 2026-06-18

Pointwise is Pointless? A Multimodal Ablation Study for Precipitation Nowcasting with Graph Neural Networks

arXiv:2606.18436v1 Announce Type: cross Abstract: Sparse point observations are increasingly available for precipitation nowcasting, but it is unclear how much they improve dense radar-field forecasts. We partially address this question with a multimodal graph neural network nowcasting system over the Nordic radar domain. The model predicts rain rate every five minutes up to two hours ahead and is trained with different combinations of radar history, MEPS numerical weather prediction, Netatmo surface observations, MSG satellite channels, stochastic noise, and CRPS-based ensemble losses. The study is designed as an ablation of operationally relevant information sources and training objectives. We compare radar-only, NWP-informed, station-informed, satellite-informed, noise-augmented, and CRPS-based configurations using complementary diagnostics on the radar grid, at station locations, for rain onset, and through oracle, displacement, and amplitude scores. The results show that each source improves a different part of the forecast problem. MEPS stabilises radar-only extrapolation, Netatmo observations improve local station and onset diagnostics, and satellite predictors reduce some station-level biases but may activate rain too early when used deterministically. CRPS-based configurations provide the most consistent radar-grid gains, while the combined satellite and CRPS setup gives the best overall oracle/DAS score. These results do not support the conclusion that point observations are uninformative for nowcasting, but they show that local observational skill and spatially coherent radar-field skill are distinct targets. The practical implication is that sparse observations can provide useful local constraints, but their benefit for radar-like fields depends on the training loss, uncertainty representation, and how observation support is encoded in the model.

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

Fine-tuning LLMs for Passive Depression Severity Estimation from AI Mental Health Dialogue

Depression is the leading cause of disability worldwide, and early detection of symptom change is essential for timely intervention. Validated instruments such as the Patient Health Questionnaire-9 (PHQ-9) support symptom monitoring at scale, but real-world completion rates are low, introducing response bias and systematic missingness. Passive approaches that infer severity from routinely generated data could close this gap. We address this by predicting PHQ-9 total scores directly from transcripts of conversations between users and an AI mental health application, requiring only conversation text and no additional clinical data. We fine-tune a Qwen3.5-27B backbone with a regression head, augment 3,111 ground-truth labels with pseudolabels generated by a reasoning model (Claude Opus) and iteratively trained intermediate models, for a combined dataset of 6,283 users. On a held-out test set of 842 users, our best model achieves MAE = 2.6, RMSE = 4.0, Pearson r = 0.80, and AUC = 0.91 at the PHQ-9 >= 10 clinical threshold. We also find AUC > 0.87 at every severity threshold from PHQ-9 >= 3 to PHQ-9 >= 24, demonstrating that the model captures depression severity across the full clinical spectrum. This work opens the door to passive, continuous symptom monitoring in AI mental health platforms, without requiring users to complete self-report measures.

23.
arXiv (CS.AI) 2026-06-12

Creating and Evaluating K-12 GenAI Assessment Graders Through Context Engineering

arXiv:2606.12422v1 Announce Type: cross Abstract: The integration of large language models (LLMs) into educational assessment represents a transformative shift in classroom grading practices. While automated scoring systems and machine learning techniques have existed for decades, generative AI (GenAI) now enables educators to implement standards-based grading (SBG) with unprecedented efficiency and scale. This paper examines the theoretical foundations and evaluates an LLM grader that uses commercially available foundation models with context and prompt engineering to score student work against a rubric. Drawing on an empirical interrater agreement study using Massachusetts Comprehensive Assessment System (MCAS) data, we observed the Quadratic Weighted Kappa (QWK) and Proportional Reduction in Mean-Squared Error (PRMSE) across mathematics, science, and ELA, using Claude Sonnet 4, Haiku 4.5, GPT-5, and GPT-5 Mini. The results demonstrate that LLM graders, especially when based on foundational models with more parameters, achieve substantial agreement with human raters in mathematics and science assessments, while the performances vary in ELA, suggesting generic foundation models can be effective at scoring in given contexts. Additional analysis of teacher and student feedback reveals strong acceptance of AI-generated narrative feedback but skepticism toward numerical scores, suggesting that LLMs function most effectively as formative tools rather than summative evaluators. Our findings indicate that thoughtfully designed hybrid models that combine AI efficiency with teacher judgment can reduce workload, enhance feedback quality, and support equitable assessment practices without displacing professional expertise.

24.
arXiv (CS.AI) 2026-06-11

SAGE: Scalable AI Governance & Evaluation

arXiv:2602.07840v4 Announce Type: replace-cross Abstract: Evaluating relevance in large-scale search systems is fundamentally constrained by the governance gap between nuanced, resource-constrained human oversight and the high-throughput requirements of production systems. While traditional approaches rely on engagement proxies or sparse manual review, these methods often fail to capture the full scope of high-impact relevance failures. We present SAGE (Scalable AI Governance \& Evaluation), a framework that operationalizes high-quality human product judgment as a scalable evaluation signal. At the core of SAGE is a bidirectional calibration loop where natural-language Policy, curated Precedent, and an LLM Surrogate Judge co-evolve. SAGE systematically resolves semantic ambiguities and misalignments, transforming subjective relevance judgment into an executable, multi-dimensional rubric with near human-level agreement. To bridge the gap between frontier model reasoning and industrial-scale inference, we apply teacher-student distillation to transfer high-fidelity judgments into compact student surrogates at 92$\times$ lower cost. Deployed within LinkedIn Search ecosystems, SAGE guided model iteration through simulation-driven development, distilling policy-aligned models for online serving and enabling rapid offline evaluation. In production, it powered policy oversight that measured ramped model variants and detected regressions invisible to engagement metrics. Collectively, these drove a 0.25\% lift in LinkedIn daily active users.

25.
arXiv (CS.LG) 2026-06-16

The Information-Theoretic Benefit of Shared Representations under Orthogonality Constraints

arXiv:2606.16028v1 Announce Type: new Abstract: Modern deep learning architectures are increasingly multi-task and multi-modal, using a pretrained foundation model combined with task-specific, fine-tuned models. Empirically, exploiting similarity across different problems, instead of solving them individually, can significantly improve overall performance. While the generalization and sample complexity properties of multitask learning have been widely studied, the parametric complexity of joint approximation in comparison to separate approximation remains less well understood. The question is particularly relevant in modern deep learning, where models are increasingly required to satisfy structural constraints such as equivariance, conservation laws, or orthogonality. We prove lower and upper bounds on the description-length for separate and joint approximation classes, respectively, in uniform norm. We build a class of orthogonal functions by composing a shared hard feature, realized by a Rademacher-Haar wavelet series, with Sawtooth-Walsh readouts to enforce orthogonality of output coordinates. The dyadic tree structure of the Rademacher-Haar wavelet concentrates the approximation hardness in the common feature component, while the readouts act as task-specific heads. Using an information-theoretic framework, we obtain a sharp gap between the optimal approximation rates achievable by joint and separate coding. Finally, we realize this separation in a neural network model using Heaviside activations via reduction to triangle-wave approximation. Our results show that even under an orthogonality constraint joint approximation requires strictly fewer bits in compositional architectures, provided the tasks share a latent hard feature. This provides theoretical insight into the description-length-efficiency of compositional multi-output architectures and clarifies how neural networks can retain expressivity under geometric constraints.