Paper Plaza - AcademicHub

01.

medRxiv (Medicine) 2026-06-23 DOI: HASH:3f7f1388b2e14dfaa00abe51a3e85909

Intrapartum Oxytocin and Maternal Outcomes Following Vaginal and Unscheduled Cesarean Delivery

Authors:

Allouche-Kam ↗Arora ↗I. H ↗Lee ↗M. C ↗Zhang ↗Hughes ↗Dekel ↗

Objective To examine whether intrapartum synthetic oxytocin exposure for labor induction or augmentation is associated with breastfeeding and postpartum depressive and traumatic stress symptoms. Methods We studied 1,296 postpartum women who delivered at a single tertiary care center, with assessments from the third trimester through approximately two months postpartum. Intrapartum oxytocin exposure was obtained from electronic medical records. Outcomes included exclusive breastfeeding, postpartum depression, and childbirth-related traumatic stress. Analyses were stratified by delivery mode and adjusted for key maternal and obstetric covariates. Results Overall, 63.3% of participants received intrapartum oxytocin. Among participants with vaginal delivery, oxytocin exposure was associated with lower exclusive breastfeeding at two months after adjustment (58.2% vs 70.3%; adjusted RR 0.86, 95% CI 0.76- 0.97; p = 0.02), but not with postpartum mental health outcomes. Among participants with unscheduled cesarean delivery, oxytocin exposure was independently associated with higher immediate postpartum depressive symptoms (F = 4.97, p = 0.03), acute childbirth-related stress (F = 4.56, p = 0.03), and two-month childbirth-related posttraumatic stress symptoms (F = 4.30, p = 0.04), but not two-month depressive symptoms. Conclusion Intrapartum oxytocin exposure was associated with lower exclusive breastfeeding after vaginal delivery and modestly higher childbirth-related distress after unscheduled cesarean delivery. These findings suggest that oxytocin exposure may mark or contribute to postpartum vulnerability in specific delivery contexts.

Read & Discuss → View Source →

02.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2602.01425

One Probe Won't Catch Them All: Towards Targeted Deception Detection

Authors:

Vikram Natarajan ↗Devina Jain ↗Shivam Arora ↗Satvik Golechha ↗Joseph Bloom ↗

arXiv:2602.01425v2 Announce Type: replace Abstract: Linear probes are a promising approach for monitoring AI systems for deceptive behaviour. Previous work has shown that a linear classifier trained on a contrastive instruction pair and a simple dataset can achieve good performance. However, these probes exhibit notable failures even in straightforward scenarios, including spurious correlations and false positives on non-deceptive responses. In this paper, we demonstrate that deception detection is inherently heterogeneous: while a single universal probe achieves modest improvements (+0.032 AUC), post-hoc oracle analysis reveals substantially higher potential (+0.108 AUC) when probes are matched to specific deception types, and synthetic validation experiments suggest this ceiling is achievable a priori when the deception type is known in advance. Our findings reveal that instruction pairs capture deceptive intent rather than content-specific patterns, explaining why prompt choice dominates probe performance (70.6% of variance). Given this heterogeneity, we conclude that organizations should define their specific threat models and deploy appropriately matched probes rather than seeking a universal deception detector.

Read & Discuss → View Source →

03.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19725

Library-Aware Doubles and Iterative Repair for Large Language Model-Generated Unit Tests in OpenSIL Firmware

Authors:

Ma Toan Bach ↗Yuchi Zheng ↗Haingo Razafindranto ↗Tanvir Alam ↗Aric Leather ↗Ranveer Sandhu ↗Jitesh Arora ↗

arXiv:2606.19725v1 Announce Type: cross Abstract: Validating changes in low-level C firmware is expensive because unit tests (UTs) are fragile under strict build constraints, where missing headers, unresolved symbols, and dependency mismatches frequently prevent compilation and linking. This study introduces an automated UT authoring workflow for the Open-Source Silicon Initialization Library (openSIL) firmware codebase maintained by Advanced Micro Devices (AMD) that reduces manual effort through a large language model (LLM) guided multi-agent pipeline. The workflow combines automated generation of test scaffolds, library-aware creation or reuse of stubs, mocks, and fakes, and an iterative compile-dispatch repair loop driven by build logs and line-coverage feedback. We evaluate the approach using compilation success, repair iterations, dispatch success, and line coverage, with time, cost, and token usage as secondary measures. Across 76 functions under test, the workflow generated compilable UTs for 73 functions. In a configuration without line coverage guidance or retrieval augmentation, mean line coverage reached 73.9%. On a 48-function subset evaluated under both configurations, mean line coverage reached 98.8% with line-coverage guidance alone and reached 94.7% when combined with vector-database retrieval. Results show that automated generation-and-repair pipelines can substantially improve UT creation efficiency and coverage for constrained firmware environments while reducing manual debugging effort.

Read & Discuss → View Source →

04.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19704

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

Authors:

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.

Read & Discuss → View Source →

05.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2605.10840

Clin-JEPA: A Multi-Phase Co-Training Framework for Joint-Embedding Predictive Pretraining on EHR Patient Trajectories

Authors:

Yixuan Yang ↗Mehak Arora ↗Ryan Zhang ↗Baraa Abed ↗Junseob Kim ↗Tilendra Choudhary ↗Md Hassanuzzaman ↗Kevin Zhu ↗Ayman Ali ↗Chengkun Yang ↗Alasdair Edward Gent ↗Victor Moas ↗…

arXiv:2605.10840v3 Announce Type: replace-cross Abstract: We present Clin-JEPA, a multi-phase co-training framework for joint-embedding predictive (JEPA) pretraining on EHR patient trajectories. JEPA architectures have enabled latent-space planning in robotics and high-quality representation learning in vision, but extending the paradigm to EHR data – to obtain a single backbone that simultaneously forecasts patient trajectories and serves diverse downstream risk-prediction tasks without per-task fine-tuning – remains an open challenge. Existing JEPA frameworks either discard the predictor after pretraining (I-JEPA, V-JEPA) or train it on a frozen pretrained encoder (V-JEPA 2-AC), leaving the encoder unaware of the rollout signal that the retained predictor must use at inference; co-training the encoder and predictor under a shared JEPA prediction objective would supply this grounding, but naïve co-training is unstable, with representation collapse and online/target drift causing autoregressive rollout to diverge. Clin-JEPA's five-phase pretraining curriculum – predictor warmup, joint refinement, EMA target alignment, hard sync, and predictor finalization – addresses each failure mode by phase, stably co-training a Qwen3-8B-based encoder and a 92M-parameter latent trajectory predictor. On MIMIC-IV ICU data, three independent evaluations support the framework: (1) latent $\ell_1$ rollout drift uniquely converges ($-$15.7%) over 48-hour horizons while baselines and ablations diverge (+3% to +4951%); (2) the encoder learns a clinically discriminative latent geometry (deteriorating-patient cohorts displace 4.83$\times$ further than stable patients in latent space, vs $\leq$2.62$\times$ for baseline encoders); (3) a single backbone outperforms strong tabular and sequence baselines on multi-task downstream evaluation. Clin-JEPA achieves mean AUROC 0.851 on ICareFM EEP and 0.883 on 8 binary risk tasks (+0.038 and +0.041 vs baseline average).

Read & Discuss → View Source →

06.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.17542

Evaluating Large Language Models Abilities for Addressee, Turn-change, and Next Speaker Prediction in Meetings

Authors:

Ryo Fukuda ↗Takatomo Kano ↗Siddhant Arora ↗Marc Delcroix ↗Naohiro Tawara ↗Atsunori Ogawa ↗Yuya Chiba ↗Atsushi Ando ↗William Chen ↗Shinji Watanabe ↗

We investigate turn-taking in multimodal multi-party conversations using large language models (LLMs). We construct an evaluation framework for three tasks: addressee detection, turn-change prediction, and next speaker prediction. We compare supervised models trained for these tasks, text-based LLMs, multimodal LLMs (MM-LLMs), and human subjects. Experiments on the AMI corpus showed that LLMs outperformed supervised models and humans in next speaker prediction, despite not being trained on the target domain and without access to audio or visual information. An MM-LLM performed better than text-based LLMs on addressee detection and turn-change prediction but remained below human performance, indicating difficulty leveraging raw audio-visual signals. Ablation analyses revealed that conversational context was critical, particularly for next speaker prediction. We observed that human and LLM prediction patterns were similar, and intervals with frequent turn changes were difficult for both.

Read & Discuss → View Source →

07.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2602.16793

Escaping the Cognitive Well: Efficient Competition Math with Off-the-Shelf Models

Authors:

Xingyu Dang ↗Rohit Agarwal ↗Rodrigo Porto ↗Anirudh Goyal ↗Liam H Fowl ↗Sanjeev Arora ↗

arXiv:2602.16793v2 Announce Type: replace Abstract: In the past year, custom and unreleased math reasoning models reached gold medal performance on the International Mathematical Olympiad (IMO). Similar performance was then reported using large-scale inference on publicly available models but at prohibitive costs (e.g., 3000 USD per problem). In this work, we present an inference pipeline that attains best-in-class performance on IMO-style math problems at an average inference cost orders of magnitude below competing methods while using only general-purpose off-the-shelf models. Our method relies on insights about grader failure in solver-grader pipelines, which we call the Cognitive Well (iterative refinement converging to a wrong solution that the solver as well as the pipeline's internal grader consider to be basically correct). Our pipeline addresses these failure modes through conjecture extraction, wherein candidate lemmas are isolated from generated solutions and independently verified alongside their negations in a fresh environment (context detachment). On IMO-ProofBench Advanced (PB-Adv), our pipeline achieves 67.1 percent performance using Gemini 3.0 Pro with an average cost per question of approximately 31 USD. At the time of evaluation, this represented the state-of-the-art on PB-Adv among both public and unreleased models, and more than doubles the success rate of the next best publicly accessible pipeline, all at a fraction of the cost.

Read & Discuss → View Source →

08.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.16180

To forget is to preserve: Machine Unlearning for 3D medical image segmentation

Authors:

Nitesh Kumar Singh ↗Akhilesh Singh ↗Arjun Arora ↗

With new data privacy laws such as the General Data Protection Regulation (GDPR) [1] that allow individuals to ask that any of their personal information be erased from trained machine learning models, there has been a push to investigate the unlearning of data from models as a way to comply with these laws. In this regard, based on four mechanics, we consider several approximate unlearning strategies applied to the MRBrainS18 dataset [2]. We use a 3D ResNet-50 [3] as a backbone architecture for segmentation that has been pre-trained with the Med3D framework [4]. Considering the pre-trained model as a baseline, we evaluate respective retention accuracy on 2 types of subjects, i.e., retain and forget. We assess these approaches through their Dice similarity coefficient and mean absolute error (MAE) values using two separate training horizons 20 and 50 epochs. The results show that the Noisy Label strategy had the best overall trade-off with a decrease of 93% in the forget set while maintaining 84% accuracy for the retained set after 50 epochs. All other strategies showed extreme levels of forgetting at higher epoch numbers while also demonstrating catastrophic degradation of their retain set performance. The results of this study provide a strict baseline of performance metrics for unlearning on a subject-specific level and provide practitioners with clear criteria for selecting the proper strategies.

Read & Discuss → View Source →

09.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2601.16407

Jacobian Scopes: token-level causal attributions in LLMs

Authors:

Toni J. B. Liu ↗Baran Zadeo\u{g}lu ↗Nicolas Boull\'e ↗Rapha\"el Sarfati ↗Gurbir Arora ↗Christopher J. Earls ↗

Large language models (LLMs) make next-token predictions based on clues present in their context, such as semantic descriptions and in-context examples. Yet, elucidating which prior tokens most strongly influence a given prediction remains challenging due to the proliferation of layers and attention heads in modern architectures. We propose Jacobian Scopes, a suite of gradient-based, token-level causal attribution methods for interpreting LLM predictions. Grounded in perturbation theory and information geometry, Jacobian Scopes quantify how input tokens influence various aspects of a model's prediction, such as specific logits, the full predictive distribution, and model uncertainty (effective temperature). Through case studies spanning instruction understanding, translation, and in-context learning (ICL), we demonstrate how Jacobian Scopes reveal implicit political biases, uncover word- and phrase-level translation strategies, and shed light on recently debated mechanisms underlying in-context time-series forecasting. To facilitate exploration of Jacobian Scopes on custom text, we open-source our implementations and provide a cloud-hosted interactive demo at https://huggingface.co/spaces/Typony/JacobianScopes.

Read & Discuss → View Source →

10.

bioRxiv (Bioinfo) 2026-06-13 DOI: HASH:3519b1e711f9b33618770b12512bc32b

ADMETron: An AI-driven SaaS platform for comprehensive ADMET prediction and compound prioritisation

Authors:

Nair ↗D. N ↗Yadav ↗R. S ↗Jondhale ↗P. M ↗Didhate ↗Gunjal ↗Ranjit ↗Patil ↗Dawande ↗Shisode ↗…

ONTOSIGHT(R) ADMETron is an AI-driven platform designed for rapid prediction and visualization of Absorption, Distribution, Metabolism, Excretion, and Toxicity (ADMET) properties to support modern drug discovery. The platform integrates an interactive web interface with a scalable predictive engine, enabling high-throughput virtual screening and batch analysis of chemical compounds. Its core architecture combines recurrent neural network (RNN)-derived molecular embeddings from SMILES representations with physicochemical descriptors, which are subsequently modeled using gradient boosting machines (GBMs). This framework provides predictions across 34 ADMET endpoints, including physicochemical properties, absorption, CYP450 interactions, hERG liability, and mutagenicity. The predictive performance of ADMETron was evaluated using benchmark datasets from the Therapeutics Data Commons (TDC), demonstrating strong performance and generalizability across both classification and regression tasks. Beyond predictive modeling, the platform introduces an interactive radar graph-based structure-activity relationship (SAR) visualization framework that enables real-time comparison of multiple compounds and reference drugs across selected ADMET parameters. This feature facilitates intuitive interpretation of multidimensional molecular profiles and supports lead optimization and compound prioritization. Comparative assessment against widely used online ADMET tools further demonstrated broad endpoint coverage spanning pharmacokinetic, physicochemical, toxicity, and medicinal chemistry properties within a unified environment. Together, these capabilities establish ADMETron as a comprehensive platform for ADMET assessment and data-driven decision-making in drug discovery. (https://admetron.partex.ai/).

Read & Discuss → View Source →

11.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2604.12002

Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision

Authors:

Yinghui He ↗Simran Kaur ↗Adithya Bhaskar ↗Yongjin Yang ↗Jiarui Liu ↗Narutatsu Ri ↗Liam Fowl ↗Abhishek Panigrahi ↗Danqi Chen ↗Sanjeev Arora ↗

Current post-training methods in verifiable settings fall into two categories. Reinforcement learning (RLVR) relies on binary rewards, which are broadly applicable and powerful, but provide only sparse supervision during training. Distillation provides dense token-level supervision, typically obtained from an external teacher or using high-quality demonstrations. Collecting such supervision can be costly or unavailable. We propose Self-Distillation Zero (SD-Zero), a method that is substantially more training sample-efficient than RL and does not require an external teacher or high-quality demonstrations. SD-Zero trains a single model to play two roles: a Generator, which produces an initial response, and a Reviser, which conditions on that response and its binary reward to produce an improved response. We then perform on-policy self-distillation to distill the reviser into the generator, using the reviser's token distributions conditioned on the generator's response and its reward as supervision. In effect, SD-Zero trains the model to transform binary rewards into dense token-level self-supervision. On math and code reasoning benchmarks with Qwen3-4B-Instruct and Olmo-3-7B-Instruct, SD-Zero improves performance by at least 10% over the base models and outperforms strong baselines, including Rejection Fine-Tuning (RFT), GRPO, and Self-Distillation Fine-Tuning (SDFT), under the same question set and training sample budget. Extensive ablation studies show two novel characteristics of our proposed algorithm: (a) token-level self-localization, where the reviser can identify the key tokens that need to be revised in the generator's response based on reward, and (b) iterative self-evolution, where the improving ability to revise answers can be distilled back into generation performance with regular teacher synchronization. Code: https://github.com/princeton-pli/Self-Distillation-Zero.

Read & Discuss → View Source →

12.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2601.22594

Language Model Circuits Are Sparse in the Neuron Basis

Authors:

Aryaman Arora ↗Zhengxuan Wu ↗Jacob Steinhardt ↗Sarah Schwettmann ↗

The high-level concepts that a neural network uses to perform computation need not be aligned to individual neurons (Smolensky, 1986). Language model interpretability research has thus turned to techniques which decompose the neuron basis into more interpretable units of model computation, such as sparse autoencoders (SAEs). However, not all neuron-based representations are uninterpretable. For the first time, we empirically show that MLP neurons are as sparse a feature basis as SAEs. We use this finding to develop an end-to-end gradient-based attribution pipeline for circuit tracing on the MLP neuron basis, which surfaces causally effective neurons on a variety of tasks. On a standard subject-verb agreement benchmark (Marks et al., 2025), a circuit of $\approx 10^2$ MLP neurons is enough to control model behaviour. On the multi-hop city-state-capital task from (Lindsey et al., 2025), we find a circuit in which small sets of neurons encode specific latent reasoning steps (e.g. mapping a city to its state), and can be steered to change the model's output. This work thus advances automated interpretability of language models without imposing additional training costs.

Read & Discuss → View Source →

Explore the Frontier of Global Academia