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 (quant-ph) 2026-06-15

Probing Many-Body Phenomena with Atomically Thin Nuclear Spin Layers in Diamond

Authors:
Philipp J. Vetter↗Christoph Findler↗Antonio Verd\'u↗Matthias Kost↗R\'emi Blinder↗Jens Fuhrmann↗Christian Osterkamp↗Johannes Lang↗Martin B. Plenio↗Javier Prior↗Fedor Jelezko↗

arXiv:2510.27374v2 Announce Type: replace Abstract: Quantum simulation aims to recreate complex many-body phenomena in controlled environments, offering insights into dynamics that are otherwise difficult to model. Existing platforms, however, are often complex and costly to scale, typically requiring ultra pure vacuum or low temperatures. Here, we introduce a platform based on a thin, strongly interacting ${}^{13}C$ nuclear spin layer in diamond that allows controlled exploration of many-body dynamics at room temperature. Nearby nitrogen-vacancy centers enable polarization, readout, and, combined with radio-frequency fields, coherent control of the nuclear spins. We demonstrate strong, tunable interactions among the nuclear spins and use the system to probe discrete time-crystalline order across varying interaction ranges. By combining ease of use with operation at ambient temperatures, our work opens new opportunities for investigating strongly correlated many-body effects.

Read & Discuss → View Source →
03.
arXiv (quant-ph) 2026-06-24

M{\o}lmer-S{\o}rensen gates in trapped-ions chains in the presence of correlated noise

Authors:
D. V. Donchenko↗E. A. Anikin↗O. Lakhmanskaya↗K. Lakhmanskiy↗

arXiv:2606.23951v1 Announce Type: new Abstract: We analyze the impact of correlated laser frequency noise on M{\o}lmer-S{\o}rensen gates in qubit registers based on trapped-ion chains. Using perturbation theory, we calculate gate fidelities in the presence of noise with arbitrary power spectral density for different chain lengths and ion positions in the chain. With our approach, we account for simultaneous excitation of multiple phonon modes during gate operation. We find out that the impact of medium-frequency laser noise depends considerably on the positions of the ions in the chain. In contrast, low-frequency noise has similar effect for different chain lengths and ion positions.

Read & Discuss → View Source →
04.
arXiv (CS.AI) 2026-06-19

Contagion Networks: Evaluator Bias Propagation in Multi-Agent LLM Systems

Authors:
Zewen Liu↗

arXiv:2606.20493v1 Announce Type: cross Abstract: When large language models serve as evaluators in multi-agent systems, their systematic evaluation biases propagate through the agent network. We introduce Contagion Networks, a formal framework for measuring how evaluator biases spread across interacting LLM agents. In a controlled 3-agent experiment using DeepSeek-chat with three distinct evaluator bias profiles (structured, balanced, evidence-based), we measure the Cross-Agent Contagion Matrix Gamma_3 and find that evaluator biases consistently propagate between agents (gamma in [0.157, 0.352]), even within the same underlying model. We identify three propagation regimes governed by the spectral radius rho(Gamma_N), and demonstrate that homogeneous-model agents produce contagion coefficients 3-5x weaker than cross-model coefficients observed in prior work (MM-EPC: gamma approx 0.85-1.3), placing them in the suppression regime. We show that increasing evaluator committee size from k=1 to k=3 reduces effective contagion by 72.4%, providing an actionable mitigation strategy. We release the open-source Contagion Network experimental framework.

Read & Discuss → View Source →
05.
arXiv (CS.CV) 2026-06-25

Naturalness Predicts but Does Not Cause Transferability in Image Encodings of Real-World Streams

Authors:
Faruk Alpay↗Baris Basaran↗

A common practice converts a one-dimensional signal into an image so that a vision backbone pretrained on natural photographs can be reused for recognition, yet the encoded image is rarely examined. We ask how the visual naturalness of an encoded image relates to its transfer accuracy under a frozen backbone. We build WorldStream, a corpus of 299 heterogeneous current-value series from key-free public APIs (weather, air quality, earthquakes, gold and oil, equities, crypto, foreign exchange, web activity and space weather), with a nine-way source-recognition task over 3143 temporally split windows. Across seven encodings and six frozen backbones, the Frechet distance of an encoding to natural images (FID) predicts its accuracy: Spearman $\rho=-0.72$. Two controlled interventions show this is not causal in the spectrum. Our invertible encoder has a single adjustable part, a spectral exponent $\beta$ (power $\propto |f|^{-\beta}$); varying $\beta$ moves the image toward or away from the natural-image manifold at fixed content. FID is lowest near the natural value $\beta \approx 2$, but frozen accuracy stays flat and far below the structured baselines (19.2% vs. 73.0%), and FID and accuracy are only weakly related over the sweep (Pearson $-0.32$). A second intervention, phase scrambling, holds the power spectrum exactly fixed while removing local structure; now FID and accuracy fall together (Pearson $-0.89$). The cross-encoding correlation is thus mediated by local structure, not spectral naturalness: FID predicts accuracy because Inception reads the same structure the backbones do. Full fine-tuning does not close the gap (27% vs. 67%), so the deficit is structural. The encoder is exactly invertible, recovering the signal from the 8-bit image at 72.9 dB, so the image doubles as a lossless record of the data.

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

Open Materials Generation with Inference-Time Reinforcement Learning

Authors:
Philipp Hoellmer↗Stefano Martiniani↗

arXiv:2602.00424v2 Announce Type: replace Abstract: Continuous-time generative models for crystalline materials enable inverse materials design by learning to predict stable crystal structures, but incorporating explicit target properties into the generative process remains challenging. Policy-gradient reinforcement learning (RL) provides a principled mechanism for aligning generative models with downstream objectives but typically requires access to the score, which has prevented its application to flow-based models that learn only velocity fields. We introduce Open Materials Generation with Inference-time Reinforcement Learning (OMatG-IRL), a policy-gradient RL framework that operates directly on the learned velocity fields and eliminates the need for the explicit computation of the score. OMatG-IRL leverages stochastic perturbations of the underlying generation dynamics preserving the baseline performance of the pretrained generative model while enabling exploration and policy-gradient estimation at inference time. Using OMatG-IRL, we present the first application of RL to crystal structure prediction (CSP). Our method enables effective reinforcement of an energy-based objective while preserving diversity through composition conditioning, and it achieves performance competitive with score-based RL approaches. Finally, we show that OMatG-IRL can learn time-dependent velocity-annealing schedules, enabling accurate CSP with order-of-magnitude improvements in sampling efficiency and, correspondingly, reduction in generation time. The OMatG-IRL code is included in a new release of the Open Materials Generation (OMatG) framework available at https://github.com/FERMat-ML/OMatG.

Read & Discuss → View Source →
07.
arXiv (CS.AI) 2026-06-24

Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning

Authors:
Tianyuan Shi↗Canbin Huang↗Bei Li↗Xin Chen↗Xiaojun Quan↗Jingang Wang↗Qifan Wang↗

arXiv:2606.24064v1 Announce Type: new Abstract: Distilling reasoning capabilities from strong to weak language models typically involves imitating specific solution trajectories, effectively transferring what to answer rather than how to reason. This trajectory-level imitation encourages memorization of instance-specific steps rather than acquisition of transferable problem-solving skills, limiting generalization to novel problems. We propose Strategy-Guided Policy Optimization (SGPO), which replaces instance-level trajectory imitation with reusable strategy distillation. SGPO extracts structured strategy descriptions from strong-model responses and, for each problem, constructs both autonomous and strategy-guided trajectories to enable direct comparison of the model's behavior with and without strategic guidance. The framework then addresses two key questions. For how to distill, a token-level forward-KL objective selectively transfers the distributional shift induced by strategy conditioning into the unguided policy, with proximal constraints ensuring stability. For when to distill, adaptive instance-level weighting strengthens guidance when autonomous exploration falls short and reduces it as the model's own competence grows. Experiments on four mathematical benchmarks across two model families show that SGPO consistently outperforms SFT, on-policy RL, and hybrid-policy baselines, improving the average score by 2.2 points over the strongest baseline on Qwen2.5-7B-Instruct. Analysis reveals that the forward-KL objective provides an inherently selective distillation signal that outperforms direct trajectory imitation, and that strategy distillation exhibits complementary scaling with base model capability.

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

Canonical Variates in Wasserstein Metric Space

Authors:
Jia Li↗Lin Lin↗

arXiv:2405.15768v2 Announce Type: replace-cross Abstract: In this paper, we address the classification of instances represented by distributions on a vector space rather than single points. We consider classification algorithms based on pairwise distances, specifically, the Wasserstein metric between distributions. Central to our investigation is dimension reduction within the Wasserstein metric space to enhance classification accuracy. We introduce a novel approach grounded in the principle of maximizing Fisher's ratio, defined as the quotient of between-class variation to within-class variation. The directions in which this ratio is maximized are termed discriminant coordinates or canonical variates axes. In practice, both between-class and within-class variations are defined as the average squared Wasserstein distances between pairs of distributions, with the pairs either belonging to the same class or to different classes. This ratio optimization is achieved through an iterative algorithm, which alternates between optimal transport and maximization steps within the vector space. Empirical studies are conducted to assess the algorithm's convergence; and experimental results demonstrate that the dimension reduction technique substantially enhances classification performance. Moreover, the new method outperforms well-established algorithms that operate on vector representations derived from distributional data. It also exhibits robustness to variations in how instances are summarized by distributions, such as the number of components in a Gaussian mixture model (GMM) representation.

Read & Discuss → View Source →
10.
arXiv (CS.LG) 2026-06-16

Learning Hybrid Biophysical Neuron Models with Neural ODEs

Authors:
Jonas Beck↗Michael Deistler↗D\'ora Vikt\'oria Moln\'ar↗Jakob H. Macke↗Philipp Berens↗

arXiv:2606.16693v1 Announce Type: cross Abstract: Biophysical neuron models link measurements of neural activity to underlying cellular mechanisms. Yet, a central challenge is that the kinetics of many ion channels are poorly characterized, and practical simplifications – omitting channels or reducing morphological detail – introduce systematic gaps between model and biology. Bridging these gaps requires approaches that can flexibly discover unmodeled dynamics while preserving mechanistic interpretability. Here, we introduce a hybrid modeling framework that embeds neural ordinary differential equations into conductance-based biophysical models to capture unknown currents or mis-specified channel kinetics. By parameterizing the neural ODE in terms of voltage-dependent steady-state and time-constant functions, we recover interpretable gating dynamics directly from voltage recordings without assuming a functional form. We show that the hybrid model fits the gating kinetics of 2400 ion channel models and recovers unknown gating dynamics from single current-clamp recordings, generalizing to out-of-distribution stimulus regimes under realistic inputs and parameter misspecification. We also use our method to reduce a multicompartment model of a cortical neuron into a single-compartment hybrid model with a learned axial current, yielding up to an order of magnitude lower computational cost. Together, our results establish a plug-and-play framework for selectively replacing unknown components of conductance-based models with neural ODEs while preserving their mechanistic structure.

Read & Discuss → View Source →
11.
arXiv (math.PR) 2026-06-16

Small moments of the sensitivity of polynomial threshold functions

Authors:
Chun-Kai Tseng↗Alexander Volberg↗

arXiv:2606.16004v1 Announce Type: new Abstract: In the first version of Chang, Slote, Volberg, and Zhang's paper [BSA_of_PTF], the authors modify a nice recursive approach due to Kane in [Correct_exponent_for_AS] where he bounded the average sensitivity of polynomial threshold functions. In [BSA_of_PTF] Kane's argument was adopted to estimate the boolean surface area of polynomial threshold function. The bridge is a combinatorial averaging lemma considering all balanced partitions. The lemma serves as a substitute for an additive property of average sensitivity. With the lemma, one can apply a Kane-type algorithm to derive a recurrence. Solving the recurrence then gives an upper bound of $e^{C_d \sqrt{\log n}}$ for the boolean surface area. In the second version of the same paper, the authors derive a polylog upper bound for BSA of PTFs. The difference is that they use a tail estimate for the sensitivity function. With the help of a polynomial restriction lemma in [poly_restriction] they sharpen the upper bound. It is noteworthy that when applying the polynomial restriction, each coordinate is put into each part independently with equal probability. As a result, a partition does not necessarily have equal-size blocks. In other words, it may not be balanced. In this note, we first investigate the effect of different partitioning. Second, we use the recursive method in the first version to derive a polylog upper bound for $\mathbb E[s(x)^{\eta}]$ where $\eta < 1/2$. It is interesting to note the phase transition that happens at $\eta=1/2$ in both versions of the proof (but in a completely different form). Section [PhaseTr-s] treats that.

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

MLUBench: A Benchmark for Lifelong Unlearning Evaluation in MLLMs

Authors:
He Li↗Haoang Chi↗Qizhou Wang↗Yunxin Mao↗Zhiheng Zhang↗Jie Tan↗Tongliang Liu↗Wenjing Yang↗Bo Han↗

arXiv:2606.12809v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are trained on massive multimodal data, making data unlearning increasingly important as data owners may request the removal of specific content. In practice, these requests often arrive sequentially over time, giving rise to the challenging problem of MLLM Lifelong Unlearning. However, most existing benchmarks are limited in scale and scope, failing to capture the complexities of MLLM lifelong unlearning. To fill this gap, we introduce the MLUBench, a large-scale and comprehensive benchmark featuring 127 entities across 9 classes under lifelong unlearning requests. We perform extensive experiments using MLUBench and reveal that existing unlearning methods suffer from severe, cumulative degradation. More critically, we further identify the unique challenge of this problem: unlike in unimodal models, MLLM lifelong unlearning is constrained by the need to preserve multimodal alignment. Continually unlearning from one modality could degrade the entire model. To alleviate this challenge, we propose LUMoE, an effective method. Experiments demonstrate that LUMoE significantly mitigates the degradation problem faced by baselines. The source code and the MLUBench dataset are open-sourced in https://github.com/lihe-maxsize/Lifelong_Unlearning_main.

Read & Discuss → View Source →
13.
arXiv (quant-ph) 2026-06-12

More efficient Clifford+T synthesis for small-angle rotations and application to Trotterization

Authors:
Marius Bothe↗Christoph S\"underhauf↗Michael J. Witham↗Earl T. Campbell↗Nick S. Blunt↗

arXiv:2605.31544v2 Announce Type: replace Abstract: Clifford+T synthesis of rotation gates is an important routine in fault-tolerant quantum compilation. While Clifford+T synthesis is scalable, it has a high overhead of tens of T gates per rotation in practice, translating to high resource estimates for many fault-tolerant algorithms. However, these well-known results, including those using probabilistic mixtures [Quantum 7, 1208 (2023)], are independent of the rotation angle $\theta$, requiring $O(\log 1/\delta)$ T gates. We show that it is possible to do much better for small angles, reducing the T cost to $\tilde{O}(\theta^2/\delta)$, and returning to existing $O(\log1/\delta)$ results in the worst case. This is particularly important since many algorithms, such as Trotterization, are dominated by small-angle rotations. Further, we perform a detailed theoretical and numerical study of quasi-probabilities, which can further reduce the total T cost of large circuits by orders of magnitude with only a small overhead in sample complexity. We also develop a scheme based on quasi-probability mixtures of Clifford+T fallback channels. We derive new $\theta$-dependent formulas that can be used for resource estimation of fault-tolerant quantum algorithms. As an application of our results, we show that the gate cost of Trotterization circuits compiled to a Clifford+T gate set is constant in the small Trotter step size limit, and can be reduced by orders of magnitude even for large step sizes. The cost of fault-tolerant Trotterization for a variety of applications should be re-examined in light of these results. Our work dispels the widely-stated claim that Clifford+T rotation synthesis has a high cost independent of $\theta$, and further develops a scalable quasi-probability method for rotation synthesis. We also expect our results to bring forward useful early fault-tolerant quantum computing by reducing required magic state resources.

Read & Discuss → View Source →
14.
bioRxiv (Bioinfo) 2026-06-14

Somatic variant detection in normal tissues from single-cell sequencing data

Authors:
Luo↗Wang↗Dou↗Bhamidipati↗S. V↗Kalra↗Grochowski↗C. M↗Doddapaneni↗H. V↗Gibbs↗R. A↗…

A crucial advantage of single-cell sequencing (SCS) is its ability to identify somatic variants in individual cells, enabling phylogenetic analysis of cellular populations within bulk tissues. While identifying somatic variants in tumor tissues via SCS has become a common practice, doing so in normal tissues remains challenging due to the rarity of somatic variants in normal cells. To evaluate the feasibility of somatic variant calling from widely available single-nucleus RNA-seq (snRNA-seq) and single-nucleus ATAC-seq (snATAC-seq) data, we profiled a Cell-line mix of six HapMap samples prepared by the SMaHT consortium using 10x Genomics 5' snRNA-seq (12k cells with 36k mean reads per cell) and snATAC-seq (11k cells with 14k median high-quality fragments per cell) for variant calling. PacBio long-read whole genome sequencing (WGS) data (109x) generated from individual cell lines were used as ground truth. Two computational tools, Monopogen and SComatic, were used for somatic variant calling from the SCS data. Monopogen achieved single nucleotide variant (SNV) detection accuracies of 93.30% in the snRNA-seq and 99.64% in the snATAC-seq data, both of which outperformed SComatic (74.35% and 94.29%, respectively). Monopogen also consistently detected somatic SNVs at cellular fractions as low as 0.5% (2.54% in snRNA and 0.81% in snATAC) in individual samples. Notably, snATAC-seq exhibited higher genomic coverage breadth and larger number of variants detected than snRNA-seq. While the SCS data have lower overall genome coverage than that of the bulk WGS, the single-cell level variant resolution allows Monopogen to assign variants to their cells of origin with over 80% accuracy in both RNA and ATAC modalities, thereby facilitating studies of clonal evolution and cell-type-specific mutagenesis. Other benchmarking methods were also evaluated (DeepVariant, Cellsnp-lite and Mutect2) for comparison. In conclusion, our study demonstrated the feasibility of performing reliable single-cell somatic mutation calling in a cell-line mixture and discussed the strengths and limitations of current computational methods when applied to normal tissues.

Read & Discuss → View Source →
16.
arXiv (CS.AI) 2026-06-18

Skill-Guided Continuation Distillation for GUI Agents

Authors:
Zhimin Fan↗Hongwei Yu↗Yeqing Shen↗Haolong Yan↗Guozhen Peng↗Tianhao Peng↗Yudong Zhang↗Xiaowen Zhang↗Kaijun Tan↗Zheng Ge↗Xiangyu Zhang↗Daxin Jiang↗…

arXiv:2606.18890v1 Announce Type: new Abstract: Improving GUI agents typically relies on behavior cloning on expert trajectories. However, as the current policy deviates from the expert policy, it inevitably encounters policy-induced off-trajectory states during closed-loop execution, i.e., states that fall outside the expert trajectories. Since expert trajectories provide no demonstrations for these unseen states, such states receive no effective supervision, leaving the policy unable to select the correct action. To close this supervision gap, we propose Skill-Guided Continuation Distillation (SGCD), an iterative self-improvement framework. SGCD first runs the plain policy without skill guidance for a few steps to reach realistic off-trajectory states. From these states, a skill-guided policy then completes the task and produces successful continuations, which are mixed with expert trajectories to supply supervision over policy-induced off-trajectory states. The skills are extracted from both successful and failed rollouts, consisting of Continuation Plans, Critical Targets, Failure Traps, and Success Criteria. On OSWorld-Verified, SGCD improves the success rate of three base models from the low-30\% range to over 50\%, demonstrating its effectiveness and generality.

Read & Discuss → View Source →
17.
arXiv (CS.CL) 2026-06-15

Large Language Model Agents Are Not Always Faithful Self-Evolvers

Authors:
Weixiang Zhao↗Yingshuo Wang↗Yichen Zhang↗Yang Deng↗Yanyan Zhao↗Wanxiang Che↗Bing Qin↗Ting Liu↗

Self-evolving large language model (LLM) agents continually improve by accumulating and reusing past experience, yet it remains unclear whether they faithfully rely on that experience to guide their behavior. We present the first systematic investigation of experience faithfulness, the causal dependence of an agent's decisions on the experience it is given, in self-evolving LLM agents. Using controlled causal interventions on both raw and condensed forms of experience, we comprehensively evaluate four representative frameworks across 13 LLM backbones and 9 environments. Our analysis uncovers a striking asymmetry: while agents consistently depend on raw experience, they often disregard or misinterpret condensed experience, even when it is the only experience provided. This gap persists across single- and multi-agent configurations and across backbone scales. We trace its underlying causes to three factors: the semantic limitations of condensed content, internal processing biases that suppress experience, and task regimes where pretrained priors already suffice. These findings challenge prevailing assumptions about self-evolving methods and underscore the need for more faithful and reliable approaches to experience integration.

Read & Discuss → View Source →
18.
arXiv (CS.CL) 2026-06-25

Reinforcement Learning Improves Traversal of Parametric Knowledge in LLMs

Authors:
Renfei Zhang↗Manasa Kaniselvan↗Rylan Schaeffer abd Niloofar Mireshghallah↗

Reinforcement learning (RL) is often credited with improving language model reasoning at the expense of knowledge. We challenge this narrative by showing that reasoning models consistently outperform their instruction-tuned versions on pure knowledge recall tasks. These gains do not reflect newly acquired information, but rather an improved procedural skill in navigating and searching existing knowledge hierarchies within the model parameters. Structured prompting, which explicitly guides models through hierarchical traversal – recovers most of the instruct-reasoning gap across five model families. A controlled RL experiment on unseen, non-extractable facts improves recall of held-out frequent but previously inaccessible facts, ruling out simple data exposure. On depth-stratified retrieval tasks, reasoning models exhibit superior traversal as retrieval depth grows. Layerwise activation analysis further shows that while factual representations maintain high cosine similarity between instruct and reasoning models, query representations diverge noticeably, indicating that reasoning primarily reshapes how models traverse knowledge rather than the knowledge representation itself. Finally, we find that distilled models often fail to match reasoning models on knowledge recall because they imitate self-correction without acquiring the exploratory behavior needed for hierarchical navigation. Together, these findings suggest that improving factual recall in LLMs depends not only on expanding what models know but also on teaching them to navigate it – motivating future post-training methods that optimize traversal.

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

Rule Taxonomy and Evolution in AI IDEs: A Mining and Survey Study

Authors:
Guangzong Cai↗Ruiyin Li↗Peng Liang↗Zengyang Li↗Mojtaba Shahin↗

arXiv:2606.12231v1 Announce Type: cross Abstract: The adoption of AI-powered Integrated Development Environments (AI IDEs) has introduced "Rules" as a novel software artifact, allowing developers to persistently inject project-specific constraints and architectural guidelines into the context of Large Language Models (LLMs). Despite their role in aligning AI behavior with developer intent, the taxonomy, evolution, and practical impact of these rules remain largely unexplored. To bridge this gap, we conducted a mixed-methods empirical study on AI IDE rules. By mining 83 open-source projects and extracting 7,310 rules, we established a comprehensive taxonomy comprising 5 primary and 25 secondary categories. We then triangulated these artifacts with survey responses from 99 practitioners. Our analysis identified a contrast between developer priorities and actual configurations: while practitioners rate architectural constraints as highly important, rule files in repositories primarily consist of low-level workflow and code formatting constraints. Furthermore, our analysis of 1,540 rule evolution events revealed that rules are updated frequently. Repository data further indicate that rule evolution is primarily driven by constructive context expansions (29.17%) and enrichments (26.59%). In contrast, surveyed developers reported modifying rules primarily to correct AI errors (77.78%), typically by adding new negative constraints rather than editing existing ones. Finally, an artifact compliance assessment of 160 rule evolution events revealed that updating rules significantly improves the adherence of software artifacts, with the average artifact compliance rate increasing by 22.99% (from 49.14% to 72.13%) following an update. Our study provides empirical insights that can help developers optimize prompting strategies and guide tool builders in designing automated conflict-detection and context-management mechanisms for AI IDEs.

Read & Discuss → View Source →
20.
arXiv (CS.AI) 2026-06-15

FreoStream:Enhancing Stream Guardrails via Future-Aware Reasoning and Safety-Aligned Optimization

Authors:
Jianwei Wang↗Guoyang Shen↗Yanhong Wu↗Haoran Li↗Hao Peng↗Huiping Zhuang↗Cen Chen↗Ziqian Zeng↗

arXiv:2606.13737v1 Announce Type: cross Abstract: Stream guardrails enable token-level safety detection before full responses are generated. However, they often make overly conservative judgements and block those sensitive but safe tokens, which is known as over-refusal. Due to lack of full context, they also fail to detect implicitly harmful content from jailbreaking. To address these challenges, we propose FreoStream, a novel streaming guardrail framework. Specifically, FreoStream fine-tunes a LoRA module to perform Future-Aware Reasoning when the base guardrail detects unsafe tokens. The reasoning process follows a Future-Reason-Judge paradigm: predict the future, reason about the full context and give the final judgement. This design can effectively reduce over-refusal by incorporating the future information. Moreover, we introduce the Safety-Aligned Optimization module that extracts the safety-aligned component from the reasoning gradients to update the base guardrail model, thereby enhancing streaming safety detection. Extensive experiments on various safety benchmarks demonstrate that FreoStream achieves lower over-refusal rates and better jailbreak defense compared to existing streaming guardrails.

Read & Discuss → View Source →
21.
arXiv (CS.CV) 2026-06-25

BOFA: Bridge-Layer Orthogonal Low-Rank Fusion for CLIP-Based Class-Incremental Learning

Authors:
Lan Li↗Tao Hu↗Da-Wei Zhou↗Jia-Qi Yang↗Han-Jia Ye↗De-Chuan Zhan↗

Class-Incremental Learning (CIL) aims to continually learn new categories without forgetting previously acquired knowledge. Vision-language models such as CLIP offer strong transferable representations via multi-modal supervision, making them promising for CIL. However, applying CLIP to CIL poses two major challenges: (1) adapting to downstream tasks often requires additional learnable modules, increasing model complexity and susceptibility to forgetting; and (2) while multi-modal representations offer complementary strengths, existing methods have yet to fully realize their potential in effectively integrating visual and textual modalities. To address these issues, we propose BOFA (Bridge-layer Orthogonal Fusion for Adaptation), a novel framework for CIL. BOFA confines all model adaptation exclusively to CLIP's existing cross-modal bridge-layer, thereby adding no extra parameters or inference cost. To prevent forgetting within this layer, it leverages Orthogonal Low-Rank Fusion, a mechanism that constrains parameter updates to a low-rank ``safe subspace" mathematically constructed to be orthogonal to past task features. This ensures stable knowledge accumulation without data replay. Furthermore, BOFA employs a cross-modal hybrid prototype that synergizes stable textual prototypes with visual counterparts derived from our stably adapted bridge-layer, enhancing classification performance. Extensive experiments on standard benchmarks show that BOFA achieves superior accuracy and efficiency compared to existing methods.

Read & Discuss → View Source →
22.
arXiv (CS.CL) 2026-06-16

VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models

Authors:
Sen Xu↗Shixi Liu↗Wei Wang↗Jixin Min↗Yingwei Dai↗Zhibin Yin↗Yirong Chen↗Xin Zhou↗Junlin Zhang↗

This technical report introduces VibeThinker-3B, a compact dense model with 3B parameters developed to investigate how far verifiable reasoning can be pushed within a strictly small-model regime. Building upon the Spectrum-to-Signal post-training paradigm, we systematically enhance the model through an optimized pipeline that includes curriculum-based supervised fine-tuning, multi-domain reinforcement learning, and offline self-distillation. Experimental evaluations demonstrate that VibeThinker-3B achieves frontier-level performance on highly demanding verifiable tasks. Specifically, it attains a score of 94.3 on AIME26 (improving to 97.1 with claim-level test-time scaling), an 80.2 Pass@1 on LiveCodeBench v6, and exhibits strong out-of-distribution generalization with a 96.1\% acceptance rate on recent unseen LeetCode contests. This effectively places it in the performance band of first-tier reasoning systems, matching or exceeding flagship models that are orders of magnitude larger, such as DeepSeek V3.2, GLM-5, and Gemini 3 Pro. Furthermore, a score of 93.4 on IFEval confirms that this extreme reasoning enhancement does not compromise strict instruction controllability. Extending our previous 1.5B work, these findings motivate the Parametric Compression-Coverage Hypothesis, which views verifiable reasoning as compressible into compact reasoning cores, while open-domain knowledge and general-purpose competence require broad parameter coverage over facts, concepts, and long-tail scenarios. This perspective suggests that compact models are not merely deployment-efficient substitutes, but a complementary path toward frontier-level performance in parameter-dense capability regimes.

Read & Discuss → View Source →
23.
arXiv (CS.LG) 2026-06-16

Semi-Supervised Speech Confidence Detection using Pseudo-Labelling and Whisper Embeddings

Authors:
Adam Wynn↗Jingyun Wang↗Xiangyu Tan↗

arXiv:2606.16505v1 Announce Type: cross Abstract: Understanding speaker confidence is crucial in educational settings, as it can enhance personalised feedback and improve learning outcomes. This study introduces a novel framework for detecting speaker confidence by integrating human-engineered features with embeddings from the Whisper encoder. To address data limitations, a pseudo-labelling technique is employed to expand the labelled dataset, allowing the model to learn from both human-annotated and model-generated labels. The framework combines traditional speech features including pitch, volume, rate of speech, and the presence of disfluencies and stress, with Whisper embeddings, and uses a co-attention mechanism to fuse these representations and achieve an overall accuracy of 75%. This study contributes to advancing speech analysis, enabling applications that support personalised learning and speaking skill development.

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

Reversal Q-Learning

Authors:
Aditya Oberai↗Seohong Park↗Sergey Levine↗

arXiv:2606.17551v1 Announce Type: cross Abstract: Iterative generative modeling techniques, such as flow matching, provide powerful tools to model complex behaviors for effective offline reinforcement learning (RL). In this work, we propose a new off-policy RL algorithm that trains a flow policy based on prior data. Our idea starts from the "expanded" Markov decision process (MDP) framework, which treats individual flow refinement steps as separate actions in an MDP. To enable off-policy RL within this framework, we apply two techniques: we generate virtual on-policy trajectories (by "reversing" flows) to make this framework compatible with prior data, and we apply a bias-and-variance reduction technique to mitigate the curse of horizon in off-policy RL. We call the resulting algorithm Reversal Q-learning (RQL). RQL has several advantages over previous flow-based RL methods: it does not suffer from backpropagation through time, makes better use of the learned value function, and directly trains the full, expressive flow policy. Through our experiments on 50 challenging simulated robotic tasks, we show that RQL leads to the best average offline RL performance compared to state-of-the-art flow-based offline RL algorithms.

Read & Discuss → View Source →
25.
arXiv (CS.CL) 2026-06-19

SAGE-OPD: Selective Agent-Guided Intervention for Multi-Turn On-Policy Distillation

Authors:
Yuhang Zhou↗Lizhu Zhang↗Yifan Wu↗Mingyi Wang↗Bo Peng↗Jiayi Liu↗Xiangjun Fan↗Zhuokai Zhao↗

On-policy distillation (OPD) improves student models by training them on trajectories induced by their own policy, making it a promising approach for mitigating exposure bias in agent training. However, most OPD studies focus on single-turn settings, while realistic LLM agents interact with environments over multiple turns. In this regime, early errors can alter future observations and compound across the trajectory, and standard dense token-level OPD becomes brittle, as it may over-penalize semantically valid alternatives, reinforce local degeneracies such as repeated actions, and propagate unreliable teacher supervision on off-distribution histories. We propose SAGE-OPD, a verifier-free selective intervention framework specifically designed for multi-turn OPD. Instead of applying teacher supervision uniformly across all turns, SAGE-OPD first observes environment feedback and uses teacher judgment to decide whether each student response should be skipped or intervened on. To further address compounding errors, SAGE-OPD weights token-level distillation by teacher confidence, reducing the influence of uncertain teacher distributions on corrupted or ambiguous histories. Finally, SAGE-OPD applies loss normalization to preserve the overall loss scale of standard OPD while retaining selective turn-level weighting. Experiments on agent tasks show that SAGE-OPD consistently improves over baselines, achieving up to a 13.3% relative improvement in ALFWorld unseen success rate over standard OPD. Ablation studies further demonstrate that turn-level intervention, teacher confidence weighting, and loss normalization provide complementary benefits. Our results suggest that effective multi-turn OPD should remain on-policy, but teacher supervision should be selectively allocated to turns where intervention is necessary and reliable.

Read & Discuss → View Source →