中 EN
Sign In Register

Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

Sign In Register
02.
arXiv (CS.CL) 2026-06-12

GENIE: A Fine-Grained Measure for Novelty

Authors:
Ramya Namuduri↗Manya Wadhwa↗Anshun Asher Zheng↗Greg Durrett↗Junyi Jessy Li↗

Large Language Models have consistently demonstrated a lack of creativity and diversity across tasks. Prior work has focused on addressing whether models are capable of generating creative outputs. Here, we aim to consider novelty and investigate what makes model-generated content novel or not novel in a task-specific manner. We propose a fine-grained evaluation metric GENIE to measure the novelty of responses along task-specific features with respect to a population of responses. We show that unlike GENIE, holistic metrics struggle to capture the high-dimensionality of novelty and do not provide insight on which properties they target. Finally, we use GENIE to measure the effectiveness of mitigation methods that address creativity to better understand where these methods can improve novelty.

Read & Discuss → View Source →
03.
arXiv (CS.AI) 2026-06-15

Learning What to Predict: Downstream-Guided Task Design for Continued Pretraining

Authors:
Shuqi Ke↗Giulia Fanti↗

arXiv:2601.22108v2 Announce Type: replace-cross Abstract: Continued pretraining is optimized with fixed self-supervised tasks but selected by downstream performance, creating a coarse feedback loop in which practitioners evaluate checkpoints, change data mixtures or objectives, and restart runs, while individual updates remain blind to target capabilities. We ask whether a small set of verifiable downstream examples can provide step-level feedback without directly supervising the learner. We introduce V-pretraining, which decouples a learner trained only with a self-supervised loss from a lightweight task designer that constructs targets or views for unlabeled batches. Given the current learner and batch, V-pretraining scores a candidate construction by predicting the first-order reduction in downstream loss after the induced self-supervised update. The designer maximizes this value; the learner then applies the update with targets or views detached, so downstream labels never update learner parameters. We instantiate V-pretraining as adaptive top-K soft targets for language modeling and learned views or masks for self-supervised vision. Across both modalities, V-pretraining improves target capabilities without degrading generalization. Under wall-clock-matched continued pretraining, it improves GSM8K Pass@1 for Qwen models using 1,024 GSM8K examples only as feedback, including a +7.4 point single-run gain for Qwen2.5-0.5B. In vision, it improves DINOv3 transfer to ADE20K semantic segmentation and NYUv2 depth estimation while preserving ImageNet linear accuracy, suggesting that feedback-guided task construction can improve target capabilities without collapsing general-purpose representations.

Read & Discuss → View Source →
04.
arXiv (CS.LG) 2026-06-24

Anticipating the Optimism Gap: Predicting Distribution-Shift Degradation of RF-Impairment Detectors from In-Distribution Statistics

Authors:
Chakshu Baweja↗

arXiv:2606.22054v2 Announce Type: replace-cross Abstract: Detectors for GNSS radio-frequency impairments (jamming, spoofing, multipath) are usually reported with a single AUC measured on the distribution they were tuned on. That number falls once conditions move, and the size of the drop is rarely known in advance because labelled field data is scarce. We ask whether this optimism can be predicted before any out-of-distribution data is seen. On an open, parameter-grounded synthetic testbed with a tunable severity shift, we evaluate thirteen detectors (five physics baselines, full-feature logistic regression and multilayer perceptrons, and single-feature learned controls) across four impairment classes. The optimism gap, the difference between in-distribution and shifted AUC, grows monotonically as the shift deepens (mean Spearman correlation 0.50). It is driven by how many observables a detector uses rather than by whether it is learned, and it varies systematically by class. Centrally, a ridge model built only from in-distribution score statistics predicts the gap for a detector it has never seen (R^2 = 0.47) and for an impairment class it has never seen (R^2 = 0.46); both are significant against a 2000-fold permutation null (p < 0.001) and survive removing the feature that is, by construction, part of the target. The headline findings are synthetic. We then run the pre-registered protocol on three open field corpora: on Jammertest 2024 the cross-detector prediction holds (R^2 = 0.11, p = 0.009), and on SatGrid, whose spoofer power sweep gives a calibrated severity axis, in-distribution AUC overstates higher-severity AUC by up to 0.22 and to the point of sign inversion, with in-distribution AUC and realised gap perfectly rank-correlated (Spearman rho = 1.0). The mechanism survives contact with real data, at smaller magnitude than in simulation. We release the testbed, a software-receiver front end, the ingest adapters and the protocol.

Read & Discuss → View Source →
05.
arXiv (CS.LG) 2026-06-11

Scaling Laws of Global Weather Models

Authors:
Yuejiang Yu↗Langwen Huang↗Alexandru Calotoiu↗Torsten Hoefler↗

arXiv:2602.22962v2 Announce Type: replace Abstract: Data-driven models are revolutionizing weather forecasting. To optimize training efficiency and model performance, this paper analyzes empirical scaling laws within this domain. We investigate the relationship between model performance (validation loss) and three key factors: model size ($N$), dataset size ($D$), and compute budget ($C$). Across a range of models, we find that Aurora exhibits the strongest data-scaling behavior: increasing the training dataset by 10x reduces validation loss by up to 3.2x. GraphCast demonstrates the highest parameter efficiency, yet suffers from limited hardware utilization. Our compute-optimal analysis indicates that, under fixed compute budgets, allocating resources to more total training data yields greater performance gains than increasing model size. Furthermore, we analyze model shape and uncover scaling behaviors that differ fundamentally from those observed in language models: weather forecasting models consistently favor increased width over depth. These findings suggest that future weather models should prioritize wider architectures and larger effective training datasets to maximize predictive performance.

Read & Discuss → View Source →
06.
arXiv (CS.LG) 2026-06-17

Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences

Authors:
Junghyun Lee↗Minju Hong↗Kwang-Sung Jun↗Chulhee Yun↗Se-Young Yun↗

arXiv:2602.23116v3 Announce Type: replace Abstract: We consider the problem of regularized best-response max-regret minimization in online RLHF under general preferences and bandit feedback. While various regularizers are utilized to robustify alignment, known polylogarithmic regret guarantees remain heavily specific to KL. To investigate whether such fast rates extend beyond KL, we adopt the Generalized Bilinear Preference Model (GBPM) – capturing intransitive preferences over $d$-dimensional item-wise features via a rank-$2r$ skew-symmetric matrix – to isolate the impact of generic regularization. Crucially, under GBPM, we prove that the dual gap of any greedy policy is bounded by the squared estimation error, derived using only strong convexity and skew-symmetry. Under a feature coverage assumption, we establish a generic polylogarithmic regret of $\tilde{\mathcal{O}}(\eta d^4 C_{\min}^{-1} (\log T)^2 \wedge d^2 C_{\min}^{-1/2} \sqrt{T})$ with Greedy Sampling, and a dimension-wise improved regret (for well-conditioned arm-sets) of $\tilde{\mathcal{O}}(C_{\min}^{-2} \sqrt{\eta r T} \wedge r^{1/3} C_{\min}^{-4/3} T^{2/3})$ with Explore-Then-Commit, where $\eta^{-1}$ is the regularization coefficient, $T$ is the time horizon, and $C_{\min}$ is an arm-set dependent quantity. This demonstrates that ``fast'' regrets are not KL-specific, but rather a fundamental consequence of generic strongly convex geometry.

Read & Discuss → View Source →
07.
arXiv (CS.CV) 2026-06-16

FUSE: Quantifying Uncertainty in Vision-Language Models by Bayesian Fusing Epistemic and Aleatoric Uncertainty

Authors:
Harry Zhang↗Luca Carlone↗

Vision-language models (VLMs) are playing an increasingly important role across multiple domains. In many applications, such as robotics, it is crucial to quantify the uncertainty in the output of these models. } We develop FUSE, a probabilistic framework for capturing two complementary sources of uncertainty in vision-language modeling: (i) aleatoric embedding-level uncertainty derived from input data vision-language ambiguity, and (ii) epistemic model-level uncertainty estimated from the semantic response diversity of VLMs. Our approach formulates a Bayesian fusion mechanism that analytically combines these uncertainty sources to produce a scalar measure of uncertainty. This measure can be used to reliably predict the model's output correctness for downstream applications. We demonstrate that our method outperforms baselines and achieves SOTA uncertainty calibration.

Read & Discuss → View Source →
08.
arXiv (CS.CL) 2026-06-16

KVEraser: Learning to Steer KV Cache for Efficient Localized Context Erasing

Authors:
Mufei Li↗Shikun Liu↗Dongqi Fu↗Haoyu Wang↗Yinglong Xia↗Hong Li↗Hong Yan↗Pan Li↗

Post-hoc context erasing over the KV cache is challenging because a local edit has a global consequence: once a span has been processed, its influence propagates into the cached states of all subsequent tokens. This issue arises naturally in long-context LLM applications, where stale retrieved facts, incorrect tool observations, retracted user preferences, or harmful prompt injections may be identified only after prefill. Exact erasing must then recompute all tokens after the deleted span, making its computational cost depend on suffix length rather than erased-span length. We introduce KVEraser, a learned KV-cache editing method for efficient localized context erasing. Given a processed context and a span to remove, KVEraser replaces only the KV states of the erased interval with learned steering states while reusing the remaining cache unchanged. To learn a transferable erasing mechanism, we build a two-stage training pipeline: generic span-neighbor pre-training teaches the eraser to suppress the influence of the erased span, while task-specific fine-tuning adapts this capability to downstream scenarios. Experiments show that KVEraser nearly matches full recomputation in post-erasure performance on in-domain tasks across 1K–32K context lengths, while its latency increases by only 24% compared with a 17.6x increase for full recomputation. KVEraser also generalizes to unseen long-document QA tasks with harmful factual distractors, achieving the best performance among approximate baselines with a 3–4x speedup over full recomputation.

Read & Discuss → View Source →
09.
arXiv (CS.CL) 2026-06-15

Can Post-Training Turn LLMs into Good Medical Coders? An Empirical Study of Generative ICD Coding

Authors:
Ziqing Wang↗Weihao Li↗Shijie Chen↗Yuan Luo↗Kaize Ding↗

Automated International Classification of Diseases (ICD) coding is a core medical-coding task for billing, epidemiology, and clinical decision support. Generative large language models (LLMs) are often reported as weak medical coders, but this finding mainly comes from inference-time settings such as prompting, retrieval, reranking, or tool use, leaving the role of task-specific post-training underexplored. We present a controlled empirical study of post-training for generative ICD coding, comparing discriminative baselines with LLM coders across prompting, supervised fine-tuning, and reinforcement learning under a common protocol and metric set. To our knowledge, this is the first study to evaluate RL-based post-training for generative LLM coders in ICD coding. We further introduce PHI, a diagnostic curriculum that extends GRPO to refine missed-code cases. Our results show that prompting-only evaluation substantially underestimates the potential of LLMs for ICD coding. SFT provides the main capability jump, GRPO further improves code-set prediction beyond SFT, and PHI provides targeted gains on macro-level performance. These findings suggest that the main bottleneck is not the generative formulation alone, but how the model is adapted and optimized for full-taxonomy recall. We release our code, data splits, and checkpoints at https://github.com/AlexandreWANG915/LLM4ICD.

Read & Discuss → View Source →
10.
arXiv (CS.CV) 2026-06-11

DynaTok: Token-Based 4D Reconstruction from Partial Point Clouds

Authors:
Weirong Chen↗Keisuke Tateno↗Hidenobu Matsuki↗Michael Niemeyer↗Daniel Cremers↗Federico Tombari↗

We address 4D reconstruction from partial point cloud sequences, where depth-sensor observations are incomplete, unordered, and lack explicit temporal correspondences. This geometry-only setting is challenging due to missing observations and ambiguous dynamics. While recent progress has largely relied on image-based methods, existing point-based approaches typically focus on single objects, assume relatively complete inputs, or require explicit correspondences. To address these limitations, we propose DynaTok, a point-based framework for correspondence-free 4D reconstruction from partial point cloud sequences without images. DynaTok encodes frames into compact latent tokens, aggregates incomplete observations over time with a Transformer-based spatiotemporal encoder, and decouples geometry and motion through residual tokens in a unified model. A flow-matching decoder then reconstructs complete, temporally consistent 4D point-cloud sequences conditioned on the latent tokens. Experiments on object- and scene-level benchmarks demonstrate improved reconstruction quality and temporal coherence from partial point cloud observations. Project page: https://wrchen530.github.io/dynatok/.

Read & Discuss → View Source →
11.
arXiv (CS.CV) 2026-06-11

Anatomically Conditioned Recurrent Refinement for Topology-Aware Circle of Willis Segmentation

Authors:
Juraj Peri\'c↗Marija Habijan↗Dario Mu\v{z}evi\'c↗Irena Gali\'c↗Danilo Babin↗Aleksandra Pi\v{z}urica↗

Segmenting the Circle of Willis (CoW) from Magnetic Resonance Angiography (MRA) is challenging due to complex topology and thin vascular structures that are prone to fragmentation. Standard Convolutional Neural Networks (CNNs) often fail to capture these topological constraints, resulting in "broken vessel" artifacts. To address this, we propose the Anatomically Conditioned Recurrent Refinement U-Net (AC2RUNet). Our architecture decouples segmentation into two streams: a Static Stream that extracts invariant anatomical features and a lightweight Dynamic Stream that iteratively refines topological errors over time. We further introduce a dynamic curriculum learning strategy that transitions from high-recall geometric supervision to topology-aware constraints. Validated on the TopCoW dataset, AC2RUNet substantially reduces Hausdorff Distance (4.72 mm vs 9.17 mm) and Betti number errors (0.19 vs 0.40), improving topological connectivity over the nnU-Net baseline while maintaining comparable volumetric Dice.

Read & Discuss → View Source →
12.
arXiv (CS.AI) 2026-06-18

A Distributionally Robust Reinforcement Learning Framework for Constrained Urban EV Dispatch

Authors:
An Nguyen↗Hoang Nguyen↗Phuong Le↗Hung Pham↗Cuong Do↗Laurent El Ghaoui↗

arXiv:2604.25848v2 Announce Type: replace Abstract: We study city-scale control of electric-vehicle (EV) ride-hailing fleets where dispatch, repositioning, and charging decisions must respect charger and feeder limits under uncertain, spatially correlated demand and travel times. We formulate the problem as a hex-grid semi-Markov decision process (semi-MDP) with mixed actions – discrete actions for serving, repositioning, and charging, together with continuous charging power – and variable action durations. To guarantee physical feasibility during both training and deployment, the policy learns over high-level intentions produced by a masked, temperature-annealed actor. These intentions are projected at every decision step through a time-limited rolling mixed-integer linear program (MILP) that strictly enforces state-of-charge, port, and feeder constraints. To mitigate distributional shifts, we optimize a Soft Actor-Critic (SAC) agent against a Wasserstein-1 ambiguity set with a graph-aligned Mahalanobis ground metric that captures spatial correlations. The robust backup uses the Kantorovich-Rubinstein dual, a projected subgradient inner loop, and a primal-dual risk-budget update. Our architecture combines a two-layer Graph Convolutional Network (GCN) encoder, twin critics, and a value network that drives the adversary. Experiments on a large-scale EV fleet simulator built from NYC taxi data show that PD-RSAC achieves the highest net profit, reaching \$1.22M, compared with \$0.58M-\$0.70M for strong heuristic, single-agent RL, and multi-agent RL baselines, including Greedy, SAC, MAPPO, and MADDPG, while maintaining zero feeder-limit violations.

Read & Discuss → View Source →
13.
arXiv (CS.LG) 2026-06-16

MIRAGE: Auditing Anti-Muslim Bias in Frontier LLMs Across Reasoning, Agentic, and Time-Coupled Conditions

Authors:
Noor Islam S. Mohammad↗Tamim Sheikh↗

arXiv:2606.16562v1 Announce Type: new Abstract: Five years after the discovery of persistent anti-Muslim bias in large language models, most evaluations remain confined to single-turn prompt completion, a setting that no longer reflects how frontier LLMs are deployed. We introduce MIRAGE (Muslim-Identity Reasoning and Agentic Generation Evaluation), a benchmark of 1{,}200 prompts spanning three deployment-realistic conditions: direct completion, chain-of-thought reasoning, and simulated agentic decision-making across content moderation, lending triage, refugee claim summarization, and hiring screens. Across six frontier models, we find that (i) chain-of-thought reasoning amplifies rather than suppresses Muslim-violence associations by 12–34\% relative to direct completion, (ii) agentic decisions exhibit a 9–22 percentage-point asymmetry between Muslim and matched non-Muslim cases on identical evidence, and (iii) bias is sharply time-coupled to retrieved news context, increasing 18–27\% under recent-conflict retrieval. Existing prompt-based mitigations transfer poorly across our three conditions, suppressing direct-completion bias while leaving agentic asymmetry largely intact. We release MIRAGE and an open evaluation harness to support targeted mitigation research.

Read & Discuss → View Source →
14.
arXiv (CS.CV) 2026-06-25

ShutterMuse: Capture-Time Photography Guidance with MLLMs

Authors:
Jiayu Li↗Yixiao Fang↗Tianyu Hu↗Wei Cheng↗Ping Huang↗Zheheng Fan↗Gang Yu↗Xingjun Ma↗

Real-world photography requires capture-time guidance for both camera framing and subject pose. Yet existing aesthetic cropping benchmarks mainly evaluate post-hoc crop prediction and overlook subject-side recommendations, leaving the capture-time guidance capabilities of multimodal large language models (MLLMs) underexplored. To address this gap, we introduce CaptureGuide-Bench, a benchmark with two complementary tasks: photographer-side composition decision and refinement, and subject-side scene-conditioned pose recommendation. Our evaluation reveals limitations: general-purpose MLLMs can make composition decisions but lack precise refinement localization, while specialized aesthetic cropping models localize crops effectively but are limited to refinement; neither provides actionable pose guidance. To support model development, we further construct CaptureGuide-Dataset, comprising 130K samples with textual rationales and structured visual annotations, and develop ShutterMuse, a unified MLLM trained with supervised and reinforcement fine-tuning. Experiments on CaptureGuide-Bench show that ShutterMuse achieves the best overall photographer-side performance among evaluated baselines and competitive subject-side pose recommendation with substantially lower inference cost, demonstrating the potential of MLLMs as interactive assistants for photography during image capture.

Read & Discuss → View Source →
16.
arXiv (CS.AI) 2026-06-16

Prediction Bottlenecks Don't Discover Causal Structure (But Here's What They Actually Do)

Authors:
Ankit Hemant Lade↗Sai Krishna Jasti↗Indar Kumar↗Aman Chadha↗

arXiv:2605.09169v2 Announce Type: replace-cross Abstract: A Mamba state-space model trained only for next-step prediction appears to recover Granger-causal structure through a simple readout $S = |W_{out} W_{in}|$, with early experiments suggesting the phenomenon generalized across architectures and benefited from interventional data at $p < 10^{-5}$. We package the protocol used to test that claim – standardized synthetic generators (VAR/Lorenz/CauseMe-style), three intervention semantics ($do(X=c)$, soft-noise, random-forcing), edge-provenance cards on three real datasets, and size-matched control arms – as a reusable falsification benchmark, and walk the claim through it in five stages. The method-level claim does not survive: (i) a plain linear bottleneck does as well or better; (ii) tuned Lasso beats the bottleneck on synthetic CauseMe-style benchmarks, and on Lorenz-96 (the only real benchmark with unambiguous ground truth) classical PCMCI and Granger lead a tight cluster in which the bottleneck trails; (iii) the headline intervention advantage is roughly 60% a sample-size confound, and the residual disappears under standard $do(X=c)$ interventions, surviving only under a non-standard random-forcing scheme; (iv) even that residual reproduces, with a larger effect, in classical bivariate Granger – the effect is method-agnostic. What survives is a narrow characterization result; the benchmark is the lasting artifact, and each stage above is one of its control arms.

Read & Discuss → View Source →
17.
arXiv (CS.CL) 2026-06-19

Pitch Spelling Jazz Lead Sheets, Solo Transcriptions, Classical Piano and Monophonic Scores

Authors:
Augustin Bouquillard↗Florent Jacquemard↗

We present an algorithm for pitch spelling and key estimation. Given an input in MIDI-like format, containing information on note pitches (expressed in semitones relative to the lowest reference note) and bar boundaries, it estimates the appropriate note names, a global Key Signature, and a local scale for each bar. This related information elements are evaluated jointly during two stages of optimisation. During an initial 'modal' stage, a probable scale is proposed for each bar, minimising the number of accidentals to be printed in the printed score with a shortest-path search. Then, during a second stage called 'tonal', these local scales are used to estimate the Key Signature and note names that would result in the best musical notation for the entire piece. We present evaluations conducted on datasets comprising a variety of digital musical scores: jazz lead sheets taken from the Real Book, transcriptions of recordings of jazz soli and bass lines, traditional tunes, as well as classical scores for piano and monophonic instruments. Our procedure was originally designed for use in music transcription, specifically for building digital collections of jazz solos transcribed from audio recordings, for the purposes of music analysis, teaching and the preservation of cultural heritage. This method should also prove useful for other tasks related to the processing of musical notation. Furthermore, to this end, we have defined new distances between various common jazz scales, which may be of some interest to musicological studies.

Read & Discuss → View Source →
18.
arXiv (CS.AI) 2026-06-12

EWAM: An Enhanced World Action Model for Closed-Loop Online Adaptation in Embodied Intelligence

Authors:
Xin Zhou↗Cong Miao↗

arXiv:2606.12690v1 Announce Type: cross Abstract: In this paper, we propose the Enhanced World Action Model (EWAM), a closed-loop online adaptation architecture built upon a pretrained and fully frozen Cosmos3 backbone network. Evaluated entirely under a zero-shot task protocol, EWAM is centrally focused on reducing the amount of additional deployment data required to adapt to new task layouts. Notably, no extra task-specific demonstration sets were introduced in any of the evaluations, and no fine-tuning was performed on the backbone network. Its performance gains stem entirely from an inference-time co-reasoning mechanism composed of four inserted lightweight neural layers: the Neural Experience Memory Layer located in the intermediate layers of the Diffusion Transformer (DiT) provides task-relevant execution context; the Neural Anomaly Detection Layer after the state prediction head monitors the divergence between predicted and actual states in real time; the Neural Policy Routing Layer dynamically selects direct execution, conservative replanning, or rollback recovery based on the anomaly severity; and the Neural Action Correction Layer refines the generated action chunks using execution diagnostics. Unlike naive feature fusion, the memory, anomaly detection, and correction modules are deeply integrated into the Cosmos3 forward path in a differentiable manner, with only the final routing decision being a discrete supervised one.

Read & Discuss → View Source →
19.
medRxiv (Medicine) 2026-06-18

The Effectiveness of aromatherapy and its supportive Interventions on anxiety and pain among breast cancer patients: A systematic review and meta-analysis

Authors:
Estervil↗N. O↗Carmichael↗C. L↗Feyissa↗G. T↗

Introduction: Breast cancer treatments are often associated with pain and anxiety, which can hinder physical functioning and overall quality of life, even after treatment. Complementary therapies, such as aromatherapy, can be used to alleviate pain and reduce anxiety in breast cancer patients. This project aimed to synthesize current global evidence on the effectiveness of aromatherapy. Method: This systematic review followed the PRISMA 2020 guidelines, with a comprehensive, systematic search conducted in PubMed, CINAHL, Cochrane Library, and SCOPUS for randomized controlled trials (RCTS) published from 2015 to 2025. Eligible studies included adult women breast cancer surgery patients who received aromatherapy during various periods of breast cancer. Where possible, data from the included studies were pooled using meta-analysis. GRADE approach was used to assess certainty of findings. Results: The search yielded 84 studies. Out of these, six were included in this review. On average, aromatherapy reduces pain and anxiety scores by 0.79 (standard mean difference (SMD)=-0.79, 95% CI -1.42, -0.16) and 0.53 (SMD=-0.53, 95 CI=-0.90, -0.16) units, respectively, compared to control condition [Low-quality of evidence]. The combination of aromatherapy with music reduces pain and anxiety by 1.26 (SMD= -1.26, 95 CI=-1.65, -0.87) and 1.08 (SMD = -1.08, 95 % CI: -1.45, -0.70) units respectively compared to standard care [Low-quality of evidence]. Conclusion: There is a potential role for the use of aromatherapy and music therapy, to alleviate anxiety and pain, especially for non-preoperative anxiety and pain. Further research is needed to inform the integration of aromatherapy into the management of anxiety and pain.

Read & Discuss → View Source →
20.
arXiv (CS.AI) 2026-06-11

Subliminal Learning Is Steering Vector Distillation

Authors:
Camila Blank↗Agam Bhatia↗Senthooran Rajamanoharan↗Arthur Conmy↗Neel Nanda↗

arXiv:2606.00995v3 Announce Type: replace Abstract: Subliminal learning refers to a student language model acquiring a teacher's traits (e.g. a system-prompted preference for owls) when fine-tuned on the teacher's outputs, despite the outputs being semantically unrelated to those traits. It remains poorly understood how data without semantic meaning can transfer specific semantic traits. In this work, we show that subliminal learning is mediated by a single steering vector, i.e. a vector added to the model's activations. Across two open-source models, we find that the teacher's system prompt is well approximated by a steering vector, and that the student's behavior is driven by learning an aligned vector over fine-tuning. System prompts that are not well approximated by steering vectors are not subliminally learned. This is a special case of steering vector distillation, in which a student trained on the outputs of a steered teacher learns to imitate that steering. We demonstrate steering vector distillation on a range of semantic and random vectors. Adding a semantic vector to a model's activations can have both model-independent and model-specific (i.e. non-semantic) effects on its behavior, so generated data that is non-semantic can transmit a vector with semantic effects, enabling subliminal learning. This also explains why subliminal learning does not transfer between models. We find that adaptive optimizers are necessary for subliminal learning in language models: activation gradients on steered data carry a small but consistent component along the steering direction, and non-adaptive optimizers impede this by allowing outlier gradients to dominate.

Read & Discuss → View Source →
21.
arXiv (CS.CV) 2026-06-18

Stimulus Motion Perception Studies Imply Specific Neural Computations in Human Visual Stabilization

Authors:
David W Arathorn↗Josephine C. D'Angelo↗Austin Roorda↗

Even during fixation the human eye is constantly in low amplitude motion, jittering over small angles in random directions at up to 100Hz. This motion results in all features of the image on the retina constantly traversing a number of cones, yet objects which are stable in the world are perceived to be stable, and any object which is moving in the world is perceived to be moving. A series of experiments carried out over a dozen years revealed the psychophysics of visual stabilization to be more nuanced than might be assumed, say, from the mechanics of stabilization of camera images, or what might be assumed to be the simplest solution from an evolutionary perspective. The psychophysics revealed by the experiments strongly implies a specific set of operations on retinal signals resulting in the observed stabilization behavior. The presentation is in two levels. First is a functional description of the action of the mechanism that is very likely responsible for the experimentally observed behavior. Second is a more speculative proposal of circuit-level neural elements that might implement the functional behavior.

Read & Discuss → View Source →
22.
arXiv (CS.AI) 2026-06-12

PRISMR: Overcoming Parse Collapse in Multimodal Listwise Ranking via Parameterized Representation Internalization

Authors:
Hao Jiang↗Xin Li↗Annan Wang↗Zhi Yang↗Haoxiang Zhang↗Yichi Zhang↗Weisi Lin↗

arXiv:2606.12942v1 Announce Type: new Abstract: Generative listwise ranking with Large Multimodal Models (LMMs) aims to capture global list context in a single forward pass, but its effectiveness degrades in long-context multimodal scenarios. We identify a recurring failure mode, parse collapse, where the autoregressive decoder produces fluent yet incomplete rankings by silently omitting candidates and terminating early. This failure stems from limited context utilization rather than simple formatting mistakes, making prompt engineering and constrained decoding insufficient. We propose PRISMR (Parameterized Representation Internalization for Semantic Multimodal Ranking), a framework that replaces transient in-context list processing with parametric structural conditioning. PRISMR uses a lightweight hypernetwork to encode multimodal candidates in parallel and generate item-specific LoRA weights, which are synthesized into an instance-specific adapter for a LMM. This paradigm enables more robust internalization of list structure while preserving the base model. We further introduce a large-scale multimodal review-ranking benchmark for evaluation. Experiments demonstrate that PRISMR substantially reduces parse collapse, improves listwise ranking performance, and transfers effectively across domains and instruction-tuned backbones.

Read & Discuss → View Source →
23.
arXiv (CS.CL) 2026-06-11

Energy-Efficient On-Device RAG on a Mobile NPU: System Design and Benchmark on Snapdragon X Elite

Authors:
Zhiyuan Cheng↗Longying Lai↗

Retrieval-Augmented Generation (RAG) pipelines are compute-intensive, combining embedding, retrieval, reranking, and large language model (LLM) generation. Running them entirely on-device benefits privacy, latency, and offline use, but the energy cost of CPU inference is a major barrier. We present what is, to our knowledge, the first end-to-end RAG pipeline that runs all neural stages – embedding, reranking, and LLM generation – on the Qualcomm Hexagon NPU of the Snapdragon X Elite. Profiling on a Dell XPS 13 laptop, we compare NPU-accelerated RAG against CPU and OpenCL/Adreno GPU baselines on indexing and query workloads. On indexing, the NPU achieves 9.1x higher embedding throughput and 12.3x less system energy. On a 120-query Wikipedia-passage benchmark, it delivers 18.1x faster LLM prefilling, 4.0x lower end-to-end query latency, and 4.0x less system energy than the CPU baseline; the same workload on the integrated GPU is 1.7x slower than CPU and uses 6.5x more energy than the NPU. A GPT-4.1 LLM-as-judge evaluation finds NPU answer quality on par with CPU and GPU within evaluator noise (mean 9.32 vs. 8.95 vs. 9.03 on a 1-10 rubric), with 86.7% of queries scoring identically across all three backends. On the Snapdragon X Elite / Hexagon class of laptop SoC, the NPU thus enables practical, energy-efficient on-device RAG without quality regression – a sustainable path toward green edge intelligence that we expect to generalize to comparable mobile NPUs (Apple Neural Engine, Intel NPU, MediaTek APU) as their software stacks mature.

Read & Discuss → View Source →
24.
arXiv (CS.LG) 2026-06-19

Evaluating Universal Machine Learning Force Fields Against Experimental Measurements

Authors:
Sajid Mannan↗Vaibhav Bihani↗Carmelo Gonzales↗Kin Long Kelvin Lee↗Nitya Nand Gosvami↗Sayan Ranu↗Santiago Miret↗N M Anoop Krishnan↗

arXiv:2508.05762v2 Announce Type: replace-cross Abstract: Universal machine learning force fields (UMLFFs) promise to revolutionize materials science by enabling rapid atomistic simulations across the periodic table. However, their evaluation has been limited to computational benchmarks that may not reflect real-world performance. We introduce UniFFBench, a comprehensive evaluation framework featuring the MinX dataset – a diverse collection of 1,500+ mineral systems spanning 85 elements, extreme thermodynamic conditions (0–5000 K, 0–1000 GPa), and structural complexity, including partial occupancy and disorder. This diversity, combined with experimental reference values for validation, enables assessment of UMLFF generalization across chemical space and conditions substantially beyond typical training scenarios. Our systematic evaluation of six state-of-the-art UMLFFs reveals a substantial ``reality gap'': models achieving impressive performance on computational benchmarks often fail when confronted with experimental complexity. Even the best-performing models exhibit higher density prediction error than the threshold required for practical applications. We observe disconnects between simulation stability and mechanical property accuracy, with prediction errors correlating with training data representation rather than the modeling method.

Read & Discuss → View Source →
25.
arXiv (CS.AI) 2026-06-17

WEQA: Wearable hEalth Question Answering with Query-Adaptive Agentic Reasoning

Authors:
Yuwei Zhang↗Tong Xia↗Bianca Emmerich↗Yu Yvonne Wu↗Dimitris Spathis↗Xin Liu↗Daniel McDuff↗Cecilia Mascolo↗

arXiv:2606.18147v1 Announce Type: new Abstract: Language models are remarkably capable at medical question answering, in some cases surpassing the accuracy of general physicians. However, answering questions about wearable health data remains challenging and understudied, as these ubiquitous sensors produce continuous, high-dimensional, and longitudinal data, which is non-trivial to align with text-centric distributions in LLM pretraining. The diversity of sensor modalities and user intents cannot be effectively handled by a fixed reasoning workflow or a single pretrained foundation model. To address these challenges, we propose WEQA, a query-adaptive agent framework that unifies LLM reasoning with specialized wearable analytical and modeling tools. An LLM controller is employed to synthesize execution plans and dynamically route each query to the appropriate combination of sensor analysis and pretrained models, and perform grounded response auditing with external knowledge. We also curate a benchmark spanning four open wearable datasets comprising analytic and predictive tasks in three different health domains. Experiments show that our framework is 24% more accurate than LLM and agentic baselines, and a blinded study with 12 medical experts and 8 users shows substantial gains in usefulness and clinical soundness.

Read & Discuss → View Source →