Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达,利用大语言模型自动生成交叉领域文献分析简报。

01.
arXiv (CS.LG) 2026-06-19

How to sketch a learning algorithm

作者:

arXiv:2604.07328v3 Announce Type: replace Abstract: How does the choice of training data influence an AI model? This broad question is of central importance to interpretability, privacy, and basic science. At its technical core is the data deletion problem: after a reasonable amount of precomputation, quickly predict how the model would behave in a given situation if a given subset of training data had been excluded from the learning algorithm. We present a data deletion scheme capable of predicting model outputs with vanishing error $\varepsilon$ and failure probability $\delta$ in the deep learning setting. Our precomputation and prediction algorithms are only $\tilde{O}(\log(1/\delta)/\varepsilon^2)$ factors slower than regular training and inference, respectively. The storage requirements are those of $\tilde{O}(\log(1/\delta)/\varepsilon^2)$ models. Our proof is based on an assumption that we call stability. In contrast to the assumptions made by prior work, stability appears to be fully compatible with learning powerful AI models. In support of this, we show that stability is satisfied in a minimal set of experiments with microgpt. Our code is available at https://github.com/SamSpo1/microgpt-sketch. At a technical level, our work is based on a new method for locally sketching an arithmetic circuit by computing higher-order derivatives in random complex directions. Forward-mode automatic differentiation allows cheap computation of these derivatives.

02.
arXiv (CS.AI) 2026-06-24

The Latent Bridge: A Continuous Slow-Fast Channel for Real-Time Game Agents

arXiv:2606.24470v1 Announce Type: new Abstract: A real-time agent for general computer use - with games as the most demanding case - must act within tens of milliseconds while still planning over seconds. These two regimes sit at opposite ends of the latency-quality tradeoff. A reasoning VLM (Qwen3-VL-8B-Thinking) deliberates effectively but requires ~1.5 s per response - far too slow for a 15 Hz control loop. In contrast, a reactive VLM (MiniCPM-o 4.5) acts in milliseconds but underperforms on planning-heavy tasks. We couple two frozen models of matched scale (9B reactive, 8B reasoning), leaving the communication channel as the sole trainable component. The standard coupling is a Text Bridge (T): the slow model writes a suffix the fast model reads. We introduce a learned continuous Latent Bridge (L) that projects the slow model's residuals into the fast model's input-embedding space in a LLaVA-style manner, avoiding any text round-trip; both are compared against Fast-Only (F). On 7 Atari games and a driving domain (MetaDrive), tuning the action decoder per channel on held-out seeds, the Latent Bridge matches or beats the Text Bridge in every domain: it significantly improves two games (MsPacman +57%, RoadRunner +28%) and is a safe drop-in elsewhere. Combining both channels interferes destructively (RoadRunner -96%), so only one should be used. The benefit is highly predictable: the bridge helps if and only if slow reasoning already beats fast reaction (T > F) - the Latent and Text gains over Fast-Only move together at r=0.93. MetaDrive is the controlled negative, where the Latent Bridge is demonstrably inert because the Text Bridge adds no value. We release replay recordings and reproducible pipelines.

03.
arXiv (quant-ph) 2026-06-17

Tunneling Dynamics and Time Delay in Electron Transport through Time-Dependent Barriers with Finite-Bandwidth Reservoirs

arXiv:2507.20649v2 Announce Type: replace-cross Abstract: We study a model system consisting of a tunneling barrier driven by an external harmonic field and coupled to two leads with finite bandwidth. Avoiding Floquet expansions, we derive simple expressions for the time-dependent tunneling current in the adiabatic regime. Our approach relates the barrier modulation to a measurable time delay in the steady-state periodic current. It provides a physically consistent definition of the tunneling time inside the barrier by subtracting the time delay associated with the leads from the total time delay. We find that the tunneling time always vanishes for wide/high barriers. Remarkably, the time delay persists even when the barrier becomes static, i.e., in the limit where the modulation frequency vanishes. This indicates that the time delay obtained through the introduction of an external periodic perturbation actually reflects an intrinsic property of the tunneling dynamics, rather than an effect of the external drive or of a particular system. We apply our results to the analysis of tunneling times in optical experiments and find good agreement with the experimental data.

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

Data Bias Mitigation under Coverage Constraints & The Price of Fairness

arXiv:2606.20461v1 Announce Type: new Abstract: Machine learning models have been shown to exhibit discriminatory outcomes or degraded performance for individuals at the intersection of multiple sensitive attributes, such as race and gender. This stems in part from two interrelated challenges: the lack of principled measures for quantifying bias (potentially intersectional), and insufficient representation of intersectional subgroups in training data. We extend a recent bias mitigation framework to incorporate coverage constraints that enforce sufficient representation across groups, including intersectional subgroups. Since achieving exactly zero bias for all groups may not be data efficient (meaning it may require large amounts of data), our solution trades small approximation errors in bias for greater data efficiency while satisfying coverage constraints. We also formulate bias mitigation as an integer linear program that optimizes over all mitigation strategies, and characterize the price of fairness, the minimum data modification cost, as a function of fairness tolerance. This is essential both for legal compliance, where regulations may mandate specific fairness thresholds, and for data governance, enabling practitioners to make informed trade-offs between bias reduction and data modification (particularly, data purchasing) costs. We evaluate our techniques on publicly available datasets, demonstrating that bias mitigation via our framework preserves predictive accuracy across multiple classifiers, and that coverage constraints, while motivated by statistical considerations, are essential for preserving downstream ML performance.

05.
arXiv (CS.CL) 2026-06-17

Evidence of Layered Positional and Directional Constraints in the Voynich Manuscript: Implications for Cipher-Like Structure

The Voynich Manuscript (VMS) exhibits a script of uncertain origin whose grapheme sequences have resisted linguistic analysis. We present a systematic analysis of its grapheme sequences, revealing two complementary structural layers: a character-level right-to-left optimization in word-internal sequences and a left-to-right dependency at word boundaries, a directional dissociation not observed in any of our four comparison languages (English, French, Hebrew, Arabic). We further evaluate two classes of structured generator against a four-signature joint criterion: a parametric slot-based generator and a Cardan grille implementing Rugg's (2004) gibberish hypothesis. Across their full tested parameter spaces, neither class reproduces all four signatures simultaneously. While these results do not rule out generator classes we have not tested, they provide the first quantitative benchmarks against which any future generative or cryptanalytic model of the VMS can be evaluated, and they suggest that the VMS exhibits cipher-like structural constraints that are difficult to reproduce from simple positional or frequency-based mechanisms alone.

06.
arXiv (quant-ph) 2026-06-24

Higher-Order Adiabatic Elimination in Atom-Cavity Systems and Its Impact on Spin-Squeezing Generation

arXiv:2506.22383v4 Announce Type: replace Abstract: Spin-squeezed states are metrologically useful quantum states where entanglement allows for enhanced sensing with respect to the standard quantum limit. Key challenges include the efficient preparation of spin-squeezed states and the scalability of estimation precision with the number $N$ of probes. Recently, in the context of the generation of spin-squeezed states via coupling of three-level atoms to an optical cavity, it was shown that increasing the atom-cavity coupling can be detrimental to spin squeezing generation, an effect that is not captured by the standard second-order adiabatic cavity removal approximation. We describe adiabatic elimination techniques to derive an effective Lindblad master equation up to third order for the atomic degrees of freedom. Numerical simulations show that the spin squeezing scalability loss is correctly reproduced by the reduced open system dynamics, highlighting the role of higher-order contributions. Furthermore, we conjecture an extension beyond leading order of the adiabatic elimination technique to the case of conditional dynamics under quantum non-demolition continuous measurement and fast cavity loss, whose reliability is again confirmed by numerical simulation of the dynamics and the corresponding behavior of spin squeezing as a function of $N$.

07.
arXiv (quant-ph) 2026-06-16

Excited-State Quantum Chemistry on Qumode-Based Processors via Variational Quantum Deflation

arXiv:2604.13457v3 Announce Type: replace Abstract: Variational quantum algorithms on bosonic quantum processors are an emerging paradigm for quantum chemistry calculations, exploiting the natural alignment between molecular structure and harmonic oscillator-based hardware. We introduce the qumode-based variational quantum deflation framework (QumVQD) for finding both electronic and vibrational excited state energies on qumode-based architectures. We validate the approach through electronic structure calculations on H$_{2}$ and linear H$_{4}$, where we introduce Hamming-weight filtering of the Fock basis to enforce particle number conservation and eliminate spurious eigenstates by reducing the required Hilbert space, which reduces the required number of qumodes in turn. We achieve agreement with full configuration interaction (FCI) using the STO-3G basis set within the chemical accuracy threshold at most points along the potential energy surfaces. Extending to the vibrational structure, we combine QumVQD with an existing Hamiltonian fragmentation approach based on Cartan subalgebra, allowing us to compute the vibrational eigenenergies of CO$_{2}$ and H$_{2}$S to spectroscopic accuracy with per-fragment circuits that scale as $O(N)$ in single-qumode gates and $O(N^2)$ in beam-splitter gates for $N$ qumodes. For the case of CO$_{2}$, we get total gate counts more than an order of magnitude smaller than those reported for qubit-based vibrational algorithms at this system size. These results demonstrate that bosonic quantum devices are a viable platform for excited-state quantum chemistry, particularly for vibrational problems where qubit-based methods incur substantial boson-to-qubit mapping overhead.

08.
medRxiv (Medicine) 2026-06-19

"Us with them": Co-designing a caesarean section consent and debriefing intervention in West Cameroon

Background Women-centred maternity care is a rights issue that determines the use of services. Such care ensures responsiveness to womens needs which is enacted through shared decision-making, review and response. In the West Region of Cameroon, informed consent (IC) and Debriefing for caesarean section (c-section) have been shown to be suboptimal or absent. This paper describes the participatory design of a quality-improvement hospital-based intervention. Methods From February to May 2025, we conducted a co-design process with three groups of stakeholders: 59 post c-section women and community representatives, 78 frontline c-section providers, and 29 directors of public and private hospitals. We followed four phases: planning, conducting, evaluating, and reporting. The conduct phase comprised five all-day workshops with post c-section women and community representatives, followed by five all-day workshops with the c-section providers. Finally, we held an 11th workshop with the hospital directors to scrutinize suggested interventions, evaluate their feasibility, and establish a consensus on their components. We described the intervention using the TIDieR (Template for Intervention Description and Replication) checklist. We documented the co-design process, using open-ended narratives to delineate interventions, and carried out real-time synthesis on visual aids (whiteboards and flipcharts). Intervention feasibility was quantified using a structured ad hoc matrix, while insights on facilitators and barriers were captured through qualitative free-text entries. We coupled data collection with constant comparison and triangulation through contemporaneous field notes, photographic documentation, and thematic mapping of stakeholders perceptions and interactive dynamics. Results Participants perspectives on the co-design were positive, and their motivation were very high although less than 50% reported previous involvement in co-design processes. More than 80% of participants found rated the co-design process as either good or very good. The final intervention comprised four components: (i) an in-service training; (ii) a standard operating procedure including a harmonised consent form and debriefing checklist; (ii) systematic supportive supervision, monitoring & evaluation; and (iv) a routine clinical audit. Each group of stakeholders upheld specific dimensions of the consent and debrief intervention. Post c-section women and community members emphasized emotional support, written discharge advice after debriefing, and zero tolerance of suboptimal consent and debriefing practices. Frontline c-section providers insisted on robust documentation for medico-legal protection. Hospitals Directors emphasized capacity-building and cultural friendliness. All the groups supported womans autonomous decision making. The intervention feasibility was rated high or very high by hospital directors except for the financial, infrastructural and technical domains. Conclusion This co-design process yielded a context-specific, multi-component intervention that was well accepted and deemed feasible across stakeholders. It provides a methodological approach to strengthening informed consent and debriefing as core elements of women-centred, accountable maternity care, and warrants implementation.

09.
arXiv (CS.AI) 2026-06-18

Spotlight: Synergizing Seed Exploration and Spot GPUs for DiT RL Post-Training

arXiv:2606.19004v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training of Diffusion Transformers (DiTs) is prohibitively expensive, requiring thousands of high-end GPUs. Existing works explore two directions to reduce cost: seed exploration improves training convergence by selecting high-contrast samples, yet adds compute to the critical path; spot GPUs offer 69–77\% lower cost, yet sit idle during training because DiT rollouts finish nearly simultaneously, which prevents LLM-style pipelining of rollout with training. Spot preemptions further break Sequence Parallelism (SP) groups, fragmenting GPU topology. We present Spotlight, the first system that harvests spot GPUs for DiT RL post-training. Spotlight rests on two key insights we devise: (1)~we show that exploration can tolerate stale model weights because exploration that uses the model weights from the previous iteration preserves the relative ranking of random seeds, allowing exploration to run on idle spot GPUs during training. (2)~SP reconfiguration can reuse on-node state, reducing group recovery from minutes to sub-second launches. Built on these insights, Spotlight introduces three techniques: a bandit-based exploration planner that maximizes reward variance within the training time budget, elastic sequence parallelism that reconfigures SP groups on the fly via persistent schedulers and intra-node weight copying, and a preemption-aware pull-based request scheduler that balances load and commits in-flight state upon preemption. We implement Spotlight on the open-source RL platform ROLL and evaluate it on Qwen-Image post-training. Spotlight reaches the same target validation score $4\times$ faster than baselines, reducing total cost by $1.4$-$6.4\times$ while achieving superior image quality on DeepSeek-OCR and Geneval datasets with resolution $512\times512$ and $1280\times1280$.

10.
arXiv (quant-ph) 2026-06-16

Synthesizing Arbitrary Non-Hermitian Hamiltonian with Stochastic Floquet Engineering

arXiv:2606.15664v1 Announce Type: new Abstract: The conventional Floquet engineering scheme synthesizes a given target Hamiltonian with a deterministic temporal periodic driving field. In this work, we introduce the stochastic Floquet engineering scheme that can synthesize an arbitrary non-Hermitian target Hamiltonian using a time-periodic driving field with noisy amplitude. Our method is rooted in the Hermitian dynamics taking noise as a valuable quantum resource with no need for loss or gain in prior. We apply our method to engineer a cavity Hamiltonian with dissipative coupling between Fock states, and to prepare a given quantum state from a generally arbitrary quantum state. The stochastic Floqut engineering also provides a way to generate non-unitary quantum gates, which take advantage in certain tasks compared to unitary quantum computing, without the need for ancillae or state-dependent updating.

11.
arXiv (CS.AI) 2026-06-16

TERMS-Bench: Diagnosing LLM Negotiation Agents Beyond Deal Rate

arXiv:2605.13909v2 Announce Type: replace-cross Abstract: Negotiation is a central mechanism of economic exchange, shaping markets, procurement, labor agreements, and resource allocation. It is also a canonical testbed for agentic language models, requiring multi-turn interaction under hidden preferences, strategic communication, and binding constraints. These properties make negotiation hard to evaluate: unlike math or code, it has no intrinsic verifier. Existing LLM negotiation evaluations rely on LLM-vs.-LLM interaction or aggregate outcomes such as deal rate, leaving failures opaque. We introduce Terms-Bench, short for Testbed for Economic Reasoning in Multi-turn Strategy, a Bayesian-game framework that makes the environment itself the verifier by specifying the counterpart's latent type, policy, and payoff structure. We instantiate it in bilateral price negotiation, where the counterpart's private state and simulator policy are hidden from the agent but observable to the evaluator. This turns the counterpart from a black-box opponent into a diagnostic instrument, enabling agent-attributable failure analysis and oracle-reference optimality gaps. Evaluating 13 LLM agents spanning frontier systems from major providers, Terms-Bench turns negotiation evaluation from aggregate ranking into actionable diagnosis: where agents fail, why they fail, and what to strengthen. Empirically, frontier models saturate deal rate yet diverge in surplus extraction, cue use, belief calibration, and compliance, revealing agent-specific bargaining bottlenecks masked by prior benchmarks.

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

Shopping Reasoning Bench: An Expert-Authored Benchmark for Multi-Turn Conversational Shopping Assistants

Conversational shopping assistants now serve hundreds of millions of customers, yet no existing benchmark jointly evaluates the open-ended multi-turn reasoning, domain expertise, and criterion-level quality that real shopping conversations demand. Shopping reasoning is unique among language model applications. Unlike factual question answering or verifiable code generation, it requires balancing subjective preferences, budget constraints, and cross-product trade-offs across multi-turn dialogue, capabilities absent from previous e-commerce and general-purpose benchmarks. We introduce the Shopping Reasoning Bench, an expert-authored benchmark of 525 missions (232 single-turn, 293 multi-turn) with 10863 importance-weighted binary rubrics authored by retail domain experts. These criteria are organized under a taxonomy of five reasoning categories and fifteen subcategories covering diverse demands such as preference refinement, trade-off analysis, and compatibility assessment. An evaluation of nine models across three families (GPT, Claude, Gemini) shows that pass rates reach only 57–77% overall. On multi-turn missions, all models score 13–29 points lower on optional above-and-beyond criteria than on required ones, and performance degrades 4–18 points as conversations progress. These gaps show that current models handle basic shopping assistance but fall short of expert-level advice, making Shopping Reasoning Bench a challenging testbed for future shopping assistant development.

14.
medRxiv (Medicine) 2026-06-17

Performance of five risk stratification tools for paediatric pneumonia against WHO scores using data from the PediCAP trial in sub-Saharan Africa

Background Risk stratification tools for childhood pneumonia have been proposed to improve identification of children at highest risk of death, particularly in low-resource settings. However, their added value over the WHO Integrated Management of Childhood Illness (IMCI) criteria and danger signs remains uncertain. Methods We conducted a secondary analysis of a multi-country randomised controlled trial of children without HIV hospitalised with pneumonia in Mozambique, South Africa, Uganda, Zambia, and Zimbabwe. We evaluated the performance of five published risk scores alongside WHO IMCI severity classification and danger signs. Discrimination for (1) in-hospital mortality, (2) 28-day mortality, and (3) 28-day readmission or death was assessed using area under the receiver operating characteristic curve (AUC). Comparative performance and clinical utility were examined. Results Of the 1010 participants, 18 (1.8%) died in hospital, 22 (2.2%) died in hospital or in the 7 days post-discharge, and 63 (6.2%) died or were readmitted by day 28. Univariate case-fatality rates were highest for variables associated with malnutrition, convulsions, and hypoxaemia. All risk scores demonstrated moderate discrimination for in-hospital and in-hospital+7-day mortality (AUC range approximately 0.75-0.84), with no meaningful differences between models, and performed similarly to the WHO danger signs and IMCI severity classification. In contrast, all approaches performed poorly in predicting 28-day readmission or death (AUC approximately 0.54-0.58). No risk score consistently outperformed simple clinical criteria. Conclusions In this multi-country dataset, we found no evidence that published paediatric pneumonia risk scores meaningfully outperform WHO IMCI-based clinical assessment for predicting mortality. The relatively small number of mortality events limits precision, and modest differences cannot be excluded. These findings suggest that, in low-resource settings, strengthening implementation of existing WHO clinical criteria may be more effective than adopting more complex prediction tools.

15.
arXiv (math.PR) 2026-06-17

Absolute continuity, supports and idempotent splitting in categorical probability

arXiv:2308.00651v5 Announce Type: replace Abstract: Markov categories have recently turned out to be a powerful high-level framework for probability and statistics. They accommodate purely categorical definitions of notions like conditional probability and almost sure equality, as well as proofs of fundamental results such as the Hewitt–Savage 0/1 Law, the de Finetti Theorem and the Ergodic Decomposition Theorem. In this work, we develop additional relevant notions from probability theory in the setting of Markov categories. This comprises improved versions of previously introduced definitions of absolute continuity and supports, as well as a detailed study of idempotents and idempotent splitting in Markov categories. Our main result on idempotent splitting is that every idempotent measurable Markov kernel between standard Borel spaces splits across another standard Borel space, and we derive this as an instance of a general categorical criterion for idempotent splitting in Markov categories.

16.
arXiv (quant-ph) 2026-06-25

Simulating Universal Quantum Gate Sets on Photonic OAM Qubits: Single-Qubit and Multi-Qubit Operations via Spatial Light Modulator Phase Holography

arXiv:2606.26088v1 Announce Type: new Abstract: Spatial light modulators (SLMs) have emerged as reconfigurable platforms for photonic quantum information processing, offering software-defined control over the orbital angular momentum (OAM) of light encoded in Laguerre-Gaussian (LG) beams. This paper presents a comprehensive simulation and hardware-grounded fidelity analysis of quantum gate operations implemented on the HOLOEYE LC 2012 transmissive SLM. A realistic three-channel noise model comprising 8-bit quantisation noise, twisted-nematic (TN) electronic and thermal noise, and phase-wrap clipping error is obtained from the manufacturer's datasheet without free-parameter fitting, yielding a total noise of $\sigma_{total} = 92.4mrad$. The complete universal single-qubit gate set $\{X, Y, Z, S, T, H\}$ and two-qubit entangling gates $\{CNOT, CZ, SWAP\}$ are simulated on a $512 \times 512$ computational grid. Results show that predicted gate fidelity are in the range of $F = 0.9914–0.9936$, with fork grating gates limited primarily by TN noise and phase gates achieving higher fidelity owing to zero phase-wrap clipping error. In addition, Bell state preparation via the H-CNOT circuit achieves $F(\Phi^+) = 0.9914$ after two SLM interactions. We benchmark our obtained results against six published experimental studies spanning the 78%–99.6% fidelity range. Finally, a wavelength-dependent analysis identifies 450–532 nm operation as the optimal regime for this device.

17.
medRxiv (Medicine) 2026-06-16

Fidelity-Derived Quantum Dissimilarity-Enhanced k-Nearest Neighbor Algorithm for Arterial Hypertension Prediction

We present a quantum-enhanced version of the classic k-Nearest Neighbors (kNN) classification algorithm, applied to the prediction of arterial hypertension. The traditional Euclidean distance metric of the kNN algorithm is replaced with a Fidelity-derived quantum dissimilarity measure to evaluate the similarity between data samples. We map classical real-world clinical and ECG-derived data features into quantum states via the Dense-Angle Encoding, which efficiently utilizes parameterized rotation gates to pack multiple features into minimal qubits while maintaining pure states. We evaluate the performance of the dissimilarity measure using both the noiseless state vector Simulator and the IBM Qiskit Estimator primitives. The quantum circuit demonstrates robust predictive capabilities comparable to the classical model. While it does not claim computational supremacy over the classical baseline, the framework proves that fidelity-based similarity is a physically meaningful and efficient approach for hybrid quantum classical classification.

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

Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them

Image-to-Video diffusion models leverage input images to generate visually stunning content, yet frequently produce motion that violates physical laws. We reveal a surprising finding: a 2-step generation often exhibits better physical consistency than a 50-step output from the same model. Through spectral analysis, we trace this to phase erosion during denoising; the phase degrades significantly (dropping by $\approx 18\%$ from step 2 to step 50), whereas the magnitude remains relatively stable. Building on this insight, we propose PhaseLock, a training-free framework that preserves the valid motion priors from few-step inference throughout the denoising trajectory. Rather than relying on full-step inference for physical consistency, PhaseLock extracts a motion prior from just 2 steps and enforces it onto high-fidelity generation via Latent Delta Guidance. Our approach effectively mitigates phase degradation, improving physical consistency by an average of 6.2 points across diverse models while largely maintaining visual fidelity, with negligible overhead ($1.06\times$ time, $1.02\times$ memory) and reduced reliance on expensive external guidance methods ($\sim5\times$ time). Project Page: https://dnwjddl.github.io/phaselock

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

ReFoCUS: Reinforcement-guided Frame Optimization for Contextual Understanding

Recent progress in Large Multi-modal Models (LMMs) has enabled effective vision-language reasoning, yet the ability to video understanding remains constrained by suboptimal frame selection strategies, albeit with the rapid development of video-specialized LMMs. Prior works attempted to solve this with static heuristics or external retrieval modules to feed frame-level information, but these approaches often fail to capture visual cues grounded to the given user queries conflating raw visual dynamics with true semantic relevance. In this paper, we introduce ReFoCUS (Reinforcement-guided Frame Optimization for Contextual UnderStanding), the first framework to integrate online policy-gradient reinforcement learning into frame-level optimization for video-LLMs. ReFoCUS aims to learn a frame selection policy, leveraging reward signals derived from reference models to capture their underlying scoring behavior over frame combinations that best support temporally grounded responses. To efficiently explore the large combinatorial frame space, we employ an autoregressive and query-conditional selection architecture that ensures contextual consistency while reducing complexity. Our policy learning removes the need for explicit frame-level supervision, as it implicitly discovers optimal and semantically consistent frame compositions. ReFoCUS consistently improves reasoning accuracy across multiple video QA benchmarks, demonstrating the advantage of aligning frame selection with model-internal utility.

20.
arXiv (CS.AI) 2026-06-25

FBOS-RL: Feedback-Driven Bi-Objective Synergistic Reinforcement Learning

arXiv:2605.20256v2 Announce Type: replace-cross Abstract: Reinforcement learning has become a cornerstone for aligning and unlocking the reasoning capabilities of large-scale models. At its core, the training loop of GRPO and its variants alternates between rollout sampling and policy update: the policy first samples rollouts from its action space, and then updates its parameters according to the advantages computed over them. Unlike supervised learning, where each gradient step is anchored to an explicit ground-truth target, the optimal gradient direction for updating model parameters in this setting is not known a priori; the high-quality rollouts drawn during the sampling stage therefore act as the implicit "teacher" that guides every parameter update. However, mainstream RL algorithms such as GRPO adopt a simple sampling scheme that conditions all rollouts on the same original prompt. When a task lies beyond the policy model's current capability, this sampling scheme rarely yields a high-quality rollout, leaving the policy model without a meaningful gradient direction when updating its parameters, which causes training to stall. To address this issue, we propose FBOS-RL. Specifically, we let the model perform Feedback-Guided Exploration Enhancement based on the feedback provided by the environment, and on top of this we design two mutually reinforcing training objectives: EPA and ECC. Extensive experiments demonstrate that EPA and ECC can mutually reinforce each other, forming a positive flywheel effect that significantly improves both the training efficiency and the final performance ceiling of reinforcement learning. Specifically, under both an identical number of rollouts and the same number of training steps, FBOS-RL learns substantially faster than GRPO and feedback-based baselines and ultimately attains a higher performance ceiling, while exhibiting higher policy entropy and lower gradient norms throughout training.

21.
arXiv (CS.LG) 2026-06-16

Acoustic Prompting via Stage-wise Modulation for Few-Shot Learning in Audio Language Models

arXiv:2606.15751v1 Announce Type: cross Abstract: Audio-Language Models (ALMs) have shown remarkable success in zero-shot audio classification by aligning audio waveforms with text. Recent efforts to improve downstream performance focus on learning optimal text prompts. However, previous approaches focus on the text encoder, leaving the potential of learnable prompts within the audio encoder unexplored. In this paper, we propose a novel framework that introduces trainable prompts into the audio encoder to capture task-specific acoustic features. We demonstrate that integrating audio-side prompt learning with existing text-side approaches enhances few-shot adaptation. Through extensive experiments across 11 datasets show that integrating our method as a plug-and-play module alongside existing text prompt tuning generally leads to performance improvements. These findings suggest that explicitly modulating the audio representation space effectively complements text-only prompting approaches. The code is available at https://github.com/hyebin-c/aspl.

22.
arXiv (CS.CV) 2026-06-24

ViTexQA: A Multi-Frame Temporal Perception Dataset for Video Text Question Answering

Despite remarkable progress in multimodal understanding, current MLLMs still exhibit limitations in video text understanding, particularly when semantics emerge through the integration of temporally distributed textual cues across multiple frames. This perception challenge fundamentally differs from static image text understanding, yet existing datasets fail to capture: the vast majority of questions remain answerable from single frames, inadequately reflecting real-world video text comprehension demands. To address this, we present ViTexQA, a large-scale video-text QA dataset, and FrameThinker for robust multi-frame temporal reasoning. We build ViTexQA via a quality-controlled Chain-of-Thought (CoT) annotation pipeline boosted with temporal constraints; all its QA pairs demand cross-frame text fusion to solve, enforcing true temporal reliance. FrameThinker adopts two-stage training for explicit temporal modeling: CoT-Guided Supervised Fine-Tuning (SFT) generates frame-aware reasoning chains, followed by Temporally-grounded Reinforcement Learning (RL) optimized with multi-frame coherence rewards. Evaluations show our method outperforms SOTA baselines on ViTexQA, lifting ROUGE-L by 6.3%.

23.
arXiv (CS.CL) 2026-06-15

CacheRL:Multi-Turn Tool-Calling Agents via Cached Rollouts and Hybrid Reward

We present CacheRL, a system for training small agent foundation models that achieves 92 percent process accuracy on multi-step tool-calling tasks, approaching GPT-5's 94 percent while requiring 100 times less compute. Our approach addresses three challenges in practical agent training: transferring tool-calling knowledge from large models at scale, enabling reinforcement learning without costly live tool execution, and learning robustly from noisy cached environments. CacheRL introduces three key innovations. First, a hybrid thinking trajectory pipeline augments agent trajectories with LLM-generated reasoning traces, producing training examples that teach models not only what tools to call but also why. Second, the CacheAgentLoop eliminates live execution costs through a three-tier fuzzy cache while preserving trajectory fidelity using token-level masking. Third, a cache-tier-aware reward dynamically adjusts answer-quality weights to avoid penalizing models for cache-induced limitations. Through iterative supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO), CacheRL improves Qwen3-4B-Thinking's validation reward from 0.43 to 0.78. On public agentic tool-calling benchmarks, our model achieves competitive performance against frontier models such as GPT-5. Ablation studies show that removing knowledge transfer reduces performance by 41 percent, while cache-aware rewards contribute a 17 percent improvement. Interestingly, reinforcement learning improves training stability but yields limited gains beyond strong supervised fine-tuning, suggesting that data quality and reward design play a more important role than complex optimization methods in building practical small agent models.

24.
bioRxiv (Bioinfo) 2026-06-14

Transposable elements as evolutionary substrates of proteindisorder in the human proteome

Intrinsically disordered regions (IDRs) are central contributors to protein function, evolution and human disease, yet the evolutionary routes that seed new disordered segments within pre-existing proteins are still poorly understood. Sequence insertions provide a powerful mechanism for disorder expansion, but the genomic donors of inserted IDR and its long-term conformational fate remain largely unknown. Transposable elements (TEs), abundant mobile genetic elements with distinctive compositional biases, represent compelling candidates for generating disorder within proteins. Here, we systematically mapped TE-derived segments across human proteins and isoforms, and we found that these insertions are strongly enriched in intrinsic disorder. The structural consequences of their insertion are shaped by TE class and family, reflecting the sequence biases of the elements from which they originate. Recent, Primate specific insertions preferentially generate disordered segments, whereas older insertions more frequently occupy ordered structural contexts, revealing an age-dependent transition in the conformational state of TE-derived sequences. TE-containing isoforms are expressed at lower levels than TE-free isoforms, particularly when insertions are young and disorder-rich, suggesting that intrinsic disorder may constrain the cellular tolerance of newly exonized sequences. These findings identify TEs as a major evolutionary mechanism linking genome mobility to the emergence of new disordered conformational ensembles in the human proteome.

25.
arXiv (CS.AI) 2026-06-11

Improving Generalization and Data Efficiency with Diffusion in Offline Multi-agent RL

arXiv:2307.01472v2 Announce Type: replace Abstract: We present a novel Diffusion Offline Multi-agent Model (DOM2) for offline Multi-Agent Reinforcement Learning (MARL). Different from existing algorithms that rely mainly on conservatism in policy design, DOM2 enhances policy expressiveness and diversity based on diffusion model. Specifically, we incorporate a diffusion model into the policy network and propose a trajectory-based data-reweighting scheme in training. These key ingredients significantly improve algorithm robustness against environment changes and achieve significant improvements in performance, generalization and data-efficiency. Our extensive experimental results demonstrate that DOM2 outperforms existing state-of-the-art methods in all multi-agent particle and multi-agent MuJoCo environments, and generalizes significantly better to shifted environments {(in $28$ out of $30$ settings evaluated)} thanks to its high expressiveness and diversity. Moreover, DOM2 is ultra data efficient and requires no more than $5\%$ data for achieving the same performance compared to existing algorithms (a $20\times$ improvement in data efficiency).