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
01.
medRxiv (Medicine) 2026-06-23

A pharmacometric grey zone reconciles high metronidazole resistance rates with bismuth quadruple therapy efficacy in Helicobacter pylori

Authors:
He↗Wang↗Xu↗

Summary Background Metronidazole (MET) resistance in Helicobacter pylori (H. pylori) exceeds 50-60% globally, yet MET-containing bismuth quadruple therapy (BQT) achieves &gt90% eradication in MET-resistant infections. We hypothesise this discordance stems from a structural limitation of two-fold dilution: a pharmacometric grey zone between the 128 and 256 &microg/mL breakpoints where treatable isolates are systematically misclassified as high-level resistance. Methods In a real-world cohort of 4610 treatment-na&iumlve children (2019-2024), checkerboard assays determined the bismuth-MET synergy factor (SF). Population PK/PD modelling simulated gastric MET exposure (AUC

Read & Discuss → View Source →
02.
arXiv (CS.AI) 2026-06-12

LLM-as-an-Investigator: Evidence-First Reasoning for Robust Interactive Problem Diagnosis

Authors:
Fabrizio Marozzo↗Pietro Li\`o↗

arXiv:2606.13220v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as interactive assistants for technical problem solving. However, when users provide incomplete descriptions or plausible but unverified explanations, LLMs may prematurely align with these assumptions and propose solutions before collecting sufficient evidence. We refer to this behavior as user-driven sycophancy: the tendency of an LLM to reinforce a user-provided hypothesis instead of testing alternative explanations. This paper introduces LLM-as-an-Investigator, an evidence-first agentic AI methodology for robust problem diagnosis. The approach is implemented through a Solution Investigator Agent, which estimates the ambiguity of an initial problem description, generates candidate hypotheses, asks targeted clarification questions, and updates hypothesis probabilities after each answer. Rather than producing an immediate response, the agent continues the investigation until the evidence makes one candidate explanation stronger than the alternatives. To evaluate the approach, we build a benchmark from solved technical forum threads in mechanical, electrical, and hydraulic domains. We use a three-agent evaluation pipeline in which a Problem-Solution Extractor Agent converts solved threads into structured cases, a Ground-Truth Evaluator Agent simulates the user while hiding the known solution, and the tested assistant attempts to recover the solution through dialogue. The experiments compare standard assistants, reasoning-oriented LLMs, and the proposed investigator-based model across LLM backbones. In addition to diagnostic accuracy, we analyze how standard assistants follow misleading user hypotheses in diagnostic cases. The results show that the proposed approach identifies the problem more accurately than direct prompting and reasoning-only baselines, while its evidence-first protocol helps reduce user-induced conversational bias.

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

Explaining RhythmFormer: A Systematic XAI Analysis of Periodic Sparse Attention for Remote Photoplethysmography

Authors:
Louis Chen↗Torbj\"orn E. M. Nordling↗

Remote photoplethysmography (rPPG) transformers achieve low heart-rate error on benchmarks, yet their decisions remain opaque–a growing concern as rPPG moves toward clinical heart rate estimation. Existing rPPG XAI is dominated by qualitative heatmap inspection without quantitative faithfulness metrics or physiology-grounded validation, leaving a gap between visual plausibility and auditable evidence. We address this gap. First, we adapt four attribution methods (raw attention, rollout, flow, Beyond Intuition) to RhythmFormer's bi-level routing attention with top-$k$ selection. Second, we introduce a skin coverage metric quantifying how much attribution mass falls on skin regions. Third, we adapt the SaCo faithfulness coefficient from its original classification setting to rPPG regression by using the MAE between original and perturbed predicted rPPG waveforms as the perturbation impact. Applying these tools, we quantify a multi-hop leakage effect under sparse top-$k$ routing: attention rollout and flow almost completely restores the connections that individual refined-attention layers explicitly set to zero. Beyond Intuition mitigates this via its value-projection-weighted rollout and gradient-supported mask, attaining the highest median refined skin coverage ($0.83$ vs. $0.57$ for vanilla rollout) and faithfulness ($F=0.92$) among the evaluated methods on UBFC-rPPG. Validation across diverse datasets and model variants is needed. A case study on a low-SaCo outlier further shows all four methods recovering consistently once an artefactual region is replaced, suggesting consistent SaCo behavior across attribution families in this illustrative case. Together, these metrics move XAI for rPPG toward auditable numerical evidence about spatial alignment and perturbation faithfulness, i.e. trustworthy rPPG XAI.

Read & Discuss → View Source →
04.
arXiv (CS.LG) 2026-06-12

Plan, Don't Pose: Long Composite Motion Generation with Text-Aligned BFM

Authors:
Nikolay Shvetsov↗Maksim Bobrin↗Nazar Buzun↗Anton Bozhedarov↗Dmitry V. Dylov↗

arXiv:2605.29906v2 Announce Type: replace Abstract: Text-to-motion (T2M) generation has broad applications in character animation, virtual avatars, and human-robot interaction. Existing methods typically generate pose trajectories or motion tokens directly from language, forcing a single model to handle semantic interpretation, long-horizon structure, and low-level physical realization. This coupling makes them costly and often unreliable for long, compositional, or semantically dense prompts. We propose Text2BFM, the first framework that aligns natural language with pretrained Behavioral Foundation Models (BFMs) for T2M generation without relying on heavy end-to-end motion generators. Text2BFM operates in the latent policy space of a frozen BFM, using it as an executable motion prior. A text-aligned variational behavioral bottleneck compresses BFM policy-latent sequences into compact motion representations that are compatible with language and preserve long-horizon behavioral structure. Generation is performed in this compact behavioral manifold with a lightweight conditional generator, and the resulting latent encoded behaviors are decoded into policy latents that drive the pretrained frozen BFM. By decoupling semantic planning from motion execution, Text2BFM achieves efficient, robust T2M generation and strong performance on long, compositional textual descriptions.

Read & Discuss → View Source →
05.
arXiv (CS.LG) 2026-06-16

Bridging data-driven priors via the score function for posterior sampling – Comparative review and experimental study

Authors:
Elhadji Cisse Faye↗Mame Diarra Fall↗Sylvain Delchini↗Nicolas Dobigeon↗

arXiv:2606.14800v1 Announce Type: cross Abstract: This paper reviews how a diverse set of popular data-driven priors commonly used in Bayesian inverse problems can be unified through their respective score functions. By framing these priors under this common perspective, we show that they can benefit from their straightfoward and effective integration into a recently proposed sampling algorithm. The applicability of this common framework is illustrated by considering several data-driven priors, namely regularization-by-denoising, normalizing flow-based priors, score-based generative models, and convex-ridge regularizers. For these four particular priors, the performance of the method is evaluated when conducting image inpainting and single image super-resolution. These results, as well as those obtained when restoring real images acquired in a geological context, demonstrate the efficiency of the method. This unified framework proves versatile enough to handle any posterior distribution defined by a broad class of score function-based priors, beyond the specific cases considered in this paper.

Read & Discuss → View Source →
06.
arXiv (quant-ph) 2026-06-24

Augmenting Imaginary-Time Evolution with Local Geometric Information

Authors:
Carlos L. Benavides-Riveros↗Prachi Sharma↗Fedor \v{S}imkovic IV↗

arXiv:2606.23934v1 Announce Type: new Abstract: Imaginary-time evolution (ITE) underpins a broad family of algorithms for ground-state preparation in quantum simulation and quantum many-body physics. In these methods, convergence is governed by the energy variance of the instantaneous state, causing the flow to approach the ground state only asymptotically. We introduce an augmented imaginary-time evolution (AITE) framework that replaces the standard gradient flow on the energy landscape with a geometrically informed descent along locally optimal directions, which are identified by exploiting the higher-order statistical structure of the instantaneous energy distribution. The resulting flow strictly outperforms standard ITE throughout the entire evolution and exhibits two qualitatively distinct regimes: a superlinear convergence regime, followed by an extinction regime in which the energy error vanishes exactly at a finite imaginary time, in sharp contrast to the asymptotic exponential decay of ITE. Standard ITE is recovered in the zero-skewness limit of AITE, implying that the acceleration extends naturally across the broader ITE algorithmic family.

Read & Discuss → View Source →
07.
arXiv (CS.CL) 2026-06-17

Examining the Limits of Word2Vec with Toki Pona

Authors:
Daniel Zhenhan Huang↗Hongchen Wu↗

Word2Vec's effectiveness at generating semantic embeddings has been widely validated, yet it has been tested almost exclusively on languages with large vocabulary inventories. This study examines whether Word2Vec can successfully capture semantic relationships within an extremely reduced vocabulary using data from Toki Pona, a constructed language with approximately 130 words. We sourced 1.4 million sentences (7.95 million tokens) from the Toki Pona community for training. Approximately 23% of sentences in the corpus contain non-Toki Pona tokens such as named entities, loanwords, and neologisms. To investigate whether this linguistic noise enhances or hinders performance – a topic rarely addressed in word embedding literature – we trained two distinct models: one retaining these incidental tokens and another filtering them out completely. Evaluation was conducted using quantitative methods measuring word proximity to semantic category centroids, automated silhouette scores via agglomerative clustering, and qualitative analysis utilizing representational similarity matrices compared against English. The results indicate that while sparse, non-core tokens do not affect the relative structure of the learned embeddings, they actually draw similar words closer together in the vector space. Importantly, Word2Vec's effectiveness depends more on distributional patterns than lexicon size even at this extreme lower bound.

Read & Discuss → View Source →
08.
arXiv (CS.CL) 2026-06-12

DSAEval: Evaluating Data Science Agents on a Wide Range of Real-World Data Science Problems

Authors:
Maojun Sun↗Yifei Xie↗Yue Wu↗Ruijian Han↗Binyan Jiang↗Defeng Sun↗Yancheng Yuan↗Jian Huang↗

Recent LLM-based data agents aim to automate data science tasks ranging from data analysis to deep learning. However, the open-ended nature of real-world data science problems, which often span multiple taxonomies and lack standard answers, poses a significant challenge for evaluation. To address this, we introduce DSAEval, a benchmark comprising 641 real-world data science problems grounded in 285 diverse datasets, covering both structured and unstructured data (e.g., image and text). DSAEval incorporates three distinctive features: (1) Multimodal Environment Perception, which enables agents to interpret observations from multiple modalities, including text and vision; (2) Multi-Query Interactions, which mirror the iterative and cumulative nature of real-world data science projects; and (3) Multi-Dimensional Evaluation, which provides a holistic assessment across reasoning, code, and results. We systematically evaluate 13 recent advanced agentic LLMs using DSAEval. Our results show that Claude-Sonnet-4.5 achieves the strongest overall performance, MiMo-V2-Pro and GPT-5.2 lead in duration and step efficiency, respectively, and MiMo-V2-Flash is the most cost-effective. We further demonstrate that multimodal perception consistently improves performance on vision-related tasks, with gains ranging from 2.04\% to 11.30\%. Overall, while current data science agents perform well on structured data and routine data analysis workflows, substantial challenges remain in unstructured domains. Finally, we offer critical insights and outline future research directions.

Read & Discuss → View Source →
09.
arXiv (CS.AI) 2026-06-16

Phase-Aware Guidance Injection for Recurrent MAPPO in Assembly-Line Disruption Recovery

Authors:
Xin Huang↗Yongcai Wang↗Fengyi Zhang↗Zhikun Tao↗Yunjun Han↗Naiqi Wu↗

arXiv:2606.16330v1 Announce Type: new Abstract: Disruption recovery in industrial assembly lines requires timely decisions under machine faults, worker absence, and emergency orders. Existing methods either rely on rigid handcrafted recovery logic or learn adaptive policies that do not readily exploit heterogeneous external recovery knowledge at decision time to reduce abnormal recovery time (ART) and preserve on-time delivery (OTD). To address this gap, we propose a phase-aware guidance injection framework that augments a trained recurrent MAPPO (RMAPPO) scheduling policy through logit-level action bias during evaluation. The framework provides a unified decision-time interface for rule-based, replay-based, and online LLM-based guidance, while activating intervention only during abnormal and recovery phases. Experiments on a custom AssemblyLineEnv show that high-quality rule guidance yields the strongest gains, replay-based guidance degrades smoothly under imperfect availability, and online LLM guidance still provides useful intermediate improvements. These results show that decision-time guidance injection can exploit heterogeneous recovery hints without redesigning the actor.

Read & Discuss → View Source →
10.
arXiv (CS.AI) 2026-06-18

HeRo-Q: A General Framework for Stable Low Bit Quantization via Hessian Conditioning

Authors:
Jinhao Zhang↗Yunquan Zhang↗Zicheng yan↗Boyang Zhang↗Jun Sun↗Daning Cheng↗

arXiv:2601.21626v2 Announce Type: replace-cross Abstract: Post Training Quantization (PTQ), a mainstream model compression technique, often leads to the paradoxical 'low error, high loss' phenomenon because it focuses solely on minimizing quantization error. The root cause lies in the Hessian matrix of the LLM loss landscape: a few high curvature directions are extremely sensitive to perturbations. To address this, we propose the Hessian Robust Quantization (HeRo Q) algorithm, which applies a lightweight, learnable rotation-compression matrix to the weight space prior to quantization. This joint framework reshapes the loss landscape by reducing the largest Hessian eigenvalue and reducing its max eigenvalue, thereby significantly enhancing robustness to quantization noise. HeRo-Q requires no architectural modifications, incurs negligible computational overhead, and integrates seamlessly into existing PTQ pipelines. Experiments on Llama and Qwen models show that HeRo Q consistently outperforms state of the art methods including GPTQ, AWQ, and SpinQuant not only achieving superior performance under standard W4A8 settings, but also excelling in the highly challenging W3A16 ultra low bit regime, where it boosts GSM8K accuracy on Llama3 8B to 70.15\% and effectively avoids the logical collapse commonly seen in aggressive quantization.

Read & Discuss → View Source →
11.
arXiv (CS.AI) 2026-06-19

A Neuromorphic Reinforcement Learning Framework for Efficient Pathfinding in Robotic Mobile Fulfillment Systems

Authors:
Junzhe Xu↗Zecui Zeng↗Lusong Li↗Yuetong Fang↗Renjing Xu↗

arXiv:2606.20031v1 Announce Type: cross Abstract: Dynamic environmental changes, confined workspaces, and stringent real-time constraints make pathfinding in Robotic Mobile Fulfillment Systems (RMFS) a challenging problem for conventional search- and rule-based methods, which typically suffer from high computational complexity and long decision latency. While reinforcement learning (RL) has emerged as a powerful alternative, deploying learned policies with extreme energy efficiency on resource-constrained hardware remains an open challenge. We present SDQN-RMFS, an end-to-end framework that achieves high-fidelity deployment of an RL-trained policy from a full-precision artificial neural network (ANN) through to a neuromorphic chip. By computing only when triggered by sparse events, this framework unlocks ultra-low-power RMFS pathfinding. Our full-stack pipeline operates as follows: an ANN policy is first efficiently trained via a collision-allowing strategy to densify informative trajectories, and then converted into a spiking neural network (SNN) via a hard-label knowledge distillation approach. This effectively addresses the output distribution mismatch, preserving policy capability across the ANN-to-SNN pipeline while substantially reducing inference latency. Hardware experiments demonstrate up to 11,281$\times$ energy savings and a nearly two-fold reduction in latency compared to a high-performance GPU baseline, while maintaining decision quality on par with the original trained policy. These results establish physical neuromorphic inference as a practical and energy-sustainable pathway for large-scale RMFS operations.

Read & Discuss → View Source →
12.
arXiv (CS.CV) 2026-06-16

Contrastive Learning for Seismic Horizon Tracking with Domain-Specific Priors

Authors:
Alexandre Thouvenot↗Lionel Boillot↗Vincent Gripon↗

Unsupervised 3D seismic horizon tracking faces a key limitation: signal-based propagators provide accurate trace-level alignment but often fail near faults, whereas texture-driven deep models are more robust to discontinuities, typically at the cost of labeled data requirements and reduced trace-level precision. We propose a self-supervised fusion of both paradigms in which signal-derived local horizon correspondences act as domain-specific priors to train a texture-based deep learning model. Specifically, we estimate reliable trace-to-trace flows from reflector slopes and use them to form positive pairs in a contrastive objective, while restricting training to high-confidence neighborhoods, optionally augmented with a fault mask. The objective is not to infer ambiguous correspondences close to discontinuities, but to preserve horizon identity across them. As a result, the network learns voxel-wise embeddings that preserve local signal continuity while enabling horizon propagation beyond discontinuities through similarity search. Experiments on the public F3 dataset and a faulted synthetic dataset achieve lower mean absolute error (MAE) than unsupervised baselines and competitive performance against a semi-supervised method using a single labeled slice.

Read & Discuss → View Source →
13.
arXiv (quant-ph) 2026-06-19

Entanglement Scaling and Problem Structure in Quantum Approximate and Adiabatic Optimization Algorithms

Authors:
Georgios Arapantonis↗Paraj Titum↗Gregory Quiroz↗

arXiv:2606.19502v1 Announce Type: new Abstract: Entanglement is widely regarded as a key resource underlying the power of quantum algorithms and their potential to achieve quantum advantage. With the emergence of variational quantum algorithms, however, questions have arisen regarding how entanglement relates to problem structure and algorithmic performance in near-term quantum applications. Here, we examine this relationship through the Quantum Approximate Optimization Algorithm (QAOA), a specific class of variational algorithms, applied to the MaxCut problem. We show that suboptimal variational parameter training can significantly modify the observed entanglement profile, obscuring its scaling behavior. By employing a high-performance optimizer, we find empirical evidence that QAOA exhibits entanglement scaling consistent with that of fermionic Gaussian states (up to a scaling factor) across a broad range of MaxCut instances. We further compare these results with adiabatic quantum computation, observing annealing-schedule-dependent entanglement profiles whose scaling behavior differs markedly from that of QAOA. Together, these findings provide new insight into how entanglement manifests in and distinguishes these two algorithmic paradigms, highlighting its connection to both computational performance and application structure.

Read & Discuss → View Source →
14.
arXiv (CS.AI) 2026-06-12

scLLM-DSC: LLM-Knowledge Enhanced Cross-Modal Deep Structural Clustering for Single-Cell RNA Sequencing

Authors:
Ping Xu↗Pengjiang Li↗Tian Du↗Zaitian Wang↗Jiawei Gu↗Ziyue Qiao↗Pengfei Wang↗Yuanchun Zhou↗

arXiv:2606.13007v1 Announce Type: cross Abstract: Clustering is fundamental to scRNA-seq analysis, serving as a cornerstone for identifying cell populations and resolving tissue heterogeneity. However, existing methods focus on mining numerical statistical patterns, suffering from semantic agnosticism by neglecting the intrinsic biological functions encoded by genes. While Large Language Models (LLMs) offer promising semantic capabilities, their direct adaptation to cell clustering is hindered by the structural mismatch between generative pre-training objectives and discriminative downstream tasks. To bridge this gap, we propose scLLM-DSC, a novel LLM-Knowledge Enhanced Cross-Modal Deep Structural Clustering framework. Diverging from data-driven paradigms, scLLM-DSC establishes a semantically-grounded representation by synergizing two views: a Knowledge-Driven Semantic View derived from NCBI gene priors and contextualized Cell2Sentence embeddings, and a Structure-Aware Topological View extracted via a graph-guided encoder. Crucially, we introduce a cross-modal contrastive alignment mechanism to enforce consistency between biological semantics and transcriptomic features within a unified latent space. Extensive benchmarks demonstrate that scLLM-DSC significantly outperforms eleven state-of-the-art baselines in clustering accuracy.

Read & Discuss → View Source →
15.
arXiv (CS.CL) 2026-06-11

FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse

Authors:
Lingzhi Yuan↗Chenghao Deng↗Fangxu Yu↗Souradip Chakraborty↗Mohammad Rostami↗Furong Huang↗

Large Language Model (LLM)-based multi-agent systems are increasingly powerful, but current agentic workflow optimization paradigms make an unsatisfying trade-off. Task-level methods spend substantial offline compute yet deploy only a single workflow, leaving complementary candidates unused, while query-level methods synthesize a new workflow per query at substantial inference cost. Our motivating analysis shows these paradigms are more complementary than competing: workflows discovered during offline search often solve different subsets of queries, and many queries handled by expensive query-level generation can already be solved by cheaper precomputed workflows. This suggests a different objective: rather than searching for one universally best workflow or regenerating one per instance, we should build a compact bank of reusable, complementary workflows and select among them adaptively at inference time. Doing so requires solving three coupled problems: generating complementary rather than redundant candidates, compressing them into a small deployable portfolio, and assigning each query to the right workflow under a performance-cost trade-off. To this end, we present FlowBank, a three-stage framework for portfolio-based agentic workflow optimization. Diversifying proposes DiverseFlow to steer search toward under-covered queries and produce a high-coverage candidate pool. Curating proposes CuraFlow to compress this pool into a compact portfolio with minimal redundancy. Matching casts deployment as edge-value prediction on a query-workflow bipartite graph and routes each incoming query to the portfolio member with the best predicted utility. Across five benchmarks, FlowBank achieves the highest average score among the evaluated methods while remaining cost-competitive, improving over the strongest automated and handcrafted baselines by 4.26% and 14.92% relative, respectively.

Read & Discuss → View Source →
16.
arXiv (CS.CL) 2026-06-24

SciZoom: A Large-scale Benchmark for Hierarchical Scientific Summarization across the LLM Era

Authors:
Han Jang↗Junhyeok Lee↗Kyu Sung Choi↗

The explosive growth of AI research has created unprecedented information overload, increasing the demand for scientific summarization at multiple levels of granularity beyond traditional abstracts. While LLMs are increasingly adopted for summarization, existing benchmarks remain limited in scale, target only a single granularity, and predate the LLM era. Moreover, since the release of ChatGPT in November 2022, researchers have rapidly adopted LLMs for drafting manuscripts themselves, fundamentally transforming scientific writing, yet no resource exists to analyze how this writing has evolved. To bridge these gaps, we introduce SciZoom, a benchmark comprising 44,946 papers from four top-tier ML venues (NeurIPS, ICLR, ICML, EMNLP) spanning 2020 to 2025, explicitly stratified into Pre-LLM and Post-LLM eras. SciZoom provides three hierarchical summarization targets (Abstract, Contributions, and TL;DR) achieving compression ratios up to 600:1, enabling both multi-granularity summarization research and temporal mining of scientific writing patterns. Our linguistic analysis reveals striking shifts in phrase patterns (up to 10x for formulaic expressions) and rhetorical style (23% decline in hedging), suggesting that LLM-assisted writing produces more confident yet homogenized prose. SciZoom serves as both a challenging benchmark and a unique resource for mining the evolution of scientific discourse in the generative AI era. Our code and dataset are publicly available on GitHub (https://github.com/janghana/SciZoom) and Hugging Face (https://huggingface.co/datasets/hanjang/SciZoom), respectively.

Read & Discuss → View Source →
17.
arXiv (CS.AI) 2026-06-24

Can Scale Save Us From Plasticity Loss in Large Language Models?

Authors:
J. Fernando Hernandez-Garcia↗Tom\'as Figliolia↗Beren Millidge↗

arXiv:2606.24752v1 Announce Type: new Abstract: The loss of plasticity - the ability of a network to learn new information after having already learned older information - is a fundamental challenge in creating artificial neural networks capable of continual learning. Although this phenomenon has been known for decades, it has mostly been studied in older, relatively small architectures and rarely in natural-language domains. To determine whether loss of plasticity remains a problem in the modern transformer-based LLM paradigm, we study plasticity loss in GPT-style Transformer models trained on a multilingual continual learning problem. Consistent with prior work, we find evidence of plasticity loss across models ranging from 5M to 314M non-embedding parameters, as measured by deterioration on a held-out Vietnamese probing task. We further find that the onset of plasticity loss follows a predictable scaling law, growing sublinearly with model size. These results suggest that larger models may delay the measurable effects of plasticity loss, but that increasing parameter count alone is likely to be insufficient to completely prevent it. We also find evidence of plasticity loss under stationary multilingual training, challenging the view that the phenomenon is exclusive to continual learning with abrupt task changes. Overall, our results suggest that even large Transformer language models trained on natural-language will eventually lose the ability to efficiently adapt to new data after sufficiently long training, in both continual and stationary settings.

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

Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation

Authors:
Zhilin Huang↗Hang Gao↗Ziqiang Dong↗Yuan Chen↗Yifeng Luo↗Chujun Qin↗Jingyi Wang↗Yang Yang↗Guanjun Jiang↗

arXiv:2606.18844v1 Announce Type: new Abstract: Self-distillation improves reasoning in large language models by using the model's own rollouts as training signal, typically through implicit logit-level alignment that minimizes KL divergence toward a privileged target distribution. However, because this supervision is generated via uncontrolled sampling, it provides no diagnostic insight into the model's specific errors or corrective guidance for its individual failure patterns. Consequently, the model learns to imitate a privileged distribution rather than receiving fine-grained corrections that pinpoint where and why its reasoning fails. In this paper, we propose Trajectory-Augmented Policy Optimization (TAPO), which advances self-distillation from implicit distributional alignment to explicit trajectory construction. During RL training, the model produces both correct and incorrect rollouts to the same query, and TAPO leverages this contrastive structure to construct micro-reflective corrections, new training trajectories that retain the model's erroneous reasoning up to the point of failure, then insert a natural-language diagnosis and corrected reasoning guided by a correct reference from the same sampling group. Since each trajectory is anchored in the learner's own prefix and solutions, the corrective signal preserves the model's on-policy distribution to a greater extent than the position-wise alignment imposed by KL-based methods. To integrate these trajectories, TAPO introduces difficulty-aware candidate selection at the model's capability boundary and decoupled advantage estimation to prevent gradient contamination. Experiments on AIME 2024, AIME 2025, and HMMT 2025 show that TAPO achieves consistent improvements over GRPO under the same number of training steps. Further analysis demonstrates that TAPO strengthens both first-pass reasoning and error-correction effectiveness.

Read & Discuss → View Source →
19.
arXiv (CS.LG) 2026-06-15

Learning the Context of Errors: Black-Box Online Adaptation of Time Series Foundation Models

Authors:
Xilin Dai↗Yiding Liu↗Hongjie Xia↗Yifan Hu↗Zewei Dong↗Jiang-Ming Yang↗Qiang Xu↗

arXiv:2606.14222v1 Announce Type: new Abstract: The rapid evolution of Time Series Foundation Models (TSFMs) has advanced zero-shot forecasting across diverse domains. Inspired by the current form of Large Language Models, future TSFMs may be offered as commercialized, closed-source API services. However, many existing online adaptation methods still rely on white-box access for parameter fine-tuning or gradient backpropagation. This paradigm mismatch raises a question: In black-box online adaptation for TSFMs, what should we learn? We answer this with an insight: the predictive errors of the base model are conditioned on both the input and output of the base model (i.e., the context of errors). To validate this insight, we propose ORCA (Online Residual Contextual Adaptation). We conduct extensive experiments across 5 state-of-the-art TSFMs and 8 datasets to demonstrate the effectiveness of our approach. Furthermore, through ablation studies, we quantitatively analyze the impact of different adapter learning hypotheses on the final adaptation performance in black-box online adaptation. Code available at https://github.com/Fifthky/ORCA.

Read & Discuss → View Source →
20.
arXiv (CS.LG) 2026-06-12

$\alpha$-fair heterogeneous agent reinforcement learning

Authors:
Yao-hua Franck Xu↗Tayeb Lemlouma↗Jean-Marie Bonnin↗Arnaud Braud↗

arXiv:2606.13076v1 Announce Type: cross Abstract: Cooperation in multi-agent systems is typically optimized through utilitarian objectives that maximize overall efficiency but fail to account for reward distribution, often resulting in inequitable "leader-follower" dynamics. While fairness-based approaches encourage pro-social behaviors where every agent benefits from cooperation, many current algorithms - including those utilizing reward shaping - break the stationarity of Markov Games or lack rigorous theoretical guarantees. This creates a critical gap between fair objective methods and theoretically safe learning frameworks. We propose a novel framework that bridges $\alpha$-fairness with Heterogeneous-Agent Trust Region Learning (HATRL), ensuring monotonic improvement and convergence toward Nash Equilibria. Our approach leverages a fair advantage function that dynamically weights agent utilities based on their expected returns, allowing the global objective to transition from purely utilitarian efficiency to $\alpha$-fairness welfare based on the parameter $\alpha$. We introduce two practical algorithms, $\alpha$-fair HATRPO and $\alpha$-fair HAPPO, and demonstrate through experiments in sequential social dilemmas like CleanUp and CommonHarvest that they perform better than HATRL's algorithms from a utilitarian point of view while achieving socially higher outcomes.

Read & Discuss → View Source →
21.
arXiv (CS.CV) 2026-06-16

Cross-modal Identity Mapping: Minimizing Information Loss in Modality Conversion via Reinforcement Learning

Authors:
Haonan Jia↗Shichao Dong↗Xin Dong↗Zenghui Sun↗Jin Wang↗Jinsong Lan↗Xiaoyong Zhu↗Bo Zheng↗Kaifu Zhang↗

Large Vision-Language Models (LVLMs) often omit or misrepresent critical visual content in generated image captions. Minimizing such information loss will force LVLMs to focus on image details to generate precise descriptions. However, measuring information loss during modality conversion is inherently challenging due to the modal gap between visual content and text output. In this paper, we argue that the quality of an image caption is positively correlated with the similarity between images retrieved via text search using that caption. Based on this insight, we further propose Cross-modal Identity Mapping (CIM), a reinforcement learning framework that enhances image captioning without requiring additional annotations. Specifically, the method quantitatively evaluates the information loss from two perspectives: Gallery Representation Consistency and Query-gallery Image Relevance. Supervised under these metrics, LVLM minimizes information loss and aims to achieve identity mapping from images to captions. The experimental results demonstrate the superior performance of our method in image captioning, even when compared with Supervised Fine-Tuning. Particularly, on the COCO-LN500 benchmark, CIM achieves a 20% improvement in relation reasoning on Qwen2.5-VL-7B.

Read & Discuss → View Source →
22.
arXiv (CS.AI) 2026-06-17

Learning to Decide with AI Assistance under Human-Alignment

Authors:
Nina Corvelo Benz↗Eleni Straitouri↗Manuel Gomez-Rodriguez↗

arXiv:2605.12646v2 Announce Type: replace-cross Abstract: It is widely agreed that when AI models assist decision-makers in high-stakes domains by predicting an outcome of interest, they should communicate the confidence of their predictions. However, empirical evidence suggests that decision-makers often struggle to determine when to trust a prediction based solely on this communicated confidence. In this context, recent theoretical and empirical work suggests a positive correlation between the utility of AI-assisted decision-making and the degree of alignment between the AI confidence and the decision-makers' confidence in their own predictions. Crucially, these findings do not yet elucidate the extent to which this alignment influences the complexity of learning to make optimal decisions through repeated interactions. In this paper, we address this question in the canonical case of binary predictions and binary decisions. We first show that this problem is equivalent to a two-armed online contextual learning problem with full feedback, and establish a lower bound of $\Omega (\sqrt{|H| \cdot |B| \cdot T} )$ on the expected regret any learner can attain, where $H$ and $B$ denote the sets of human and AI confidence values. We then demonstrate that, under perfect alignment between AI and human confidence, a learner can attain an expected regret of $O(\sqrt{|H| \cdot T\log T})$ and, when $\sqrt{|H|} = O(\log T)$ and $B$ is countable, a non-trivial generalization of the Dvoretzky-Kiefer-Wolfowitz inequality improves the regret bound to $O(\sqrt{T\log T})$. Taken together, these results reveal that alignment can reduce the complexity of learning to make decisions with AI assistance. Experiments on real data from two different human-subject studies where participants solve simple decision-making tasks assisted by AI models show that our theoretical results are robust to violations of perfect alignment.

Read & Discuss → View Source →
23.
arXiv (CS.AI) 2026-06-12

Different Layers, Different Manifolds: Module-Wise Weight-Space Geometry in Transformer Optimization

Authors:
Kirato Yoshihara↗

arXiv:2606.13276v1 Announce Type: cross Abstract: Weight-space geometry plays a central role in neural network optimization, yet manifold constraints are often applied uniformly across all weight matrices. In this work, we ask whether different transformer modules prefer different manifold geometries. We study Manifold Muon for GPT-2 pretraining and compare layer-wise assignments of Stiefel and DGram constraints across attention and MLP blocks. Our results show a clear asymmetry: constraining attention layers with Stiefel geometry while assigning DGram geometry to MLP layers gives the best performance among the tested configurations, whereas the inverted assignment and all-DGram configuration become unstable under the shared hyperparameter setting. We trace this failure to singular value growth in DGram-constrained attention weights, which can amplify attention logits and induce softmax saturation. These findings suggest that symmetry-aware and geometry-aware optimization for transformers should be module-specific rather than uniform.

Read & Discuss → View Source →
24.
arXiv (CS.LG) 2026-06-17

Generalization Guarantees for Multi-Input Neural Operator Learning in Sobolev Spaces

Authors:
Yahong Yang↗Zecheng Zhang↗Wei Zhu↗Wenjing Liao↗Hao Liu↗

arXiv:2606.17419v1 Announce Type: new Abstract: We develop approximation and generalization error estimates for multi-input neural operators, with the output error measured in Sobolev norms. In contrast to standard operator-learning settings with a single input function, our framework allows multiple input functions defined on possibly different domains, with different dimensions and Sobolev regularities. The derived rates explicitly quantify the contribution of each input space to the final error bound. In particular, in the balanced regime, the approximation and generalization rates are governed by the interaction between the input dimensions, regularities, and Sobolev orders, while the dependence on the model complexity retains a \(\log\log/\log\)-type structure. Our analysis provides a general theoretical framework for multi-input operator learning, including Sobolev training, and is applicable to operator learning problems arising from partial differential equations and scientific computing.

Read & Discuss → View Source →
25.
arXiv (CS.CV) 2026-06-15

RATS! Patches Talk Through Registers: Emergent Parts in Register Attention Transformers

Authors:
Timing Yang↗Predrag Neskovic↗Jansen Seheult↗Wenchao Han↗Anand Bhattad↗Alan Yuille↗Feng Wang↗

When humans see a bird, they recognize far more than just "bird" – they see a head, wings, and talons, a structured assembly of reusable parts that can be identified across every bird they have ever seen. We ask whether a self-supervised visual model can discover the same compositional structure on its own. To this end, we propose RATS (Register Attention Transformers), which decomposes the classification token into N learnable register tokens that route patch information through an L->N->N->L bottleneck via a three-step compress-communicate-broadcast attention. The N registers are partitioned across the H attention heads, so that registers assigned to different heads do not interact with each other. Without auxiliary losses or part annotations, each register spontaneously specializes into a proto-semantic region whose emerging structure resembles object parts. RATS surpasses all baselines by +12 mIoU on average across five segmentation benchmarks, with consistent gains on ADE20K (+1.11 mIoU) and COCO (+0.2 AP^m). Its register dictionary further exhibits part-level consistency and semantic proximity across related categories. Our results suggest that RATS may provide a useful architectural prior for structured and interpretable visual representation learning.

Read & Discuss → View Source →