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 (quant-ph) 2026-06-15

Collision models for open quantum systems coupled to finite environments

arXiv:2606.14163v1 Announce Type: new Abstract: We study a system qubit repeatedly interacting with the same environmental qubit, with a reservoir acting on the environment between collisions via a completely positive, trace-preserving map. We show that complete suppression of system–environment correlations uniquely requires a full environmental reset, recovering a semi group dynamics with a time-independent Gorini–Kossakowski–Sudarshan–Lindblad generator, whereas a partial reset yields a continuous transition between Markovian and non-Markovian regimes governed by a single dimensionless relaxation parameter. For a resonant excitation-exchange interaction, we obtain exact closed-form expressions for the Bloch-vector dynamics for both a generalized depolarizing channel and a generalized amplitude-damping channel acting as the reservoir-induced map. Using the Breuer–Laine–Piilo measure and a Choi-matrix CP-divisibility witness, we identify three distinct dynamical regimes across the parameter space: CP-divisible Markovian dynamics, CP-indivisible but P-divisible dynamics, and non-P-divisible non-Markovian dynamics. The boundaries between these regimes, and the structural differences between uniform and anisotropic environmental relaxation, are characterized numerically.

02.
arXiv (CS.CL) 2026-06-16

Robust Dual-Signal Fusion: Hybrid Neuro-Symbolic Gating with Compressed Chain-of-Thought Refinement for Irony Detection in Social Media Texts

Large Language Models (LLMs) natively default to literal semantic interpretations, making zero-shot irony detection a persistent challenge. We introduce the Robust Dual-Signal (RDS) Fusion framework, a hybrid neuro-symbolic architecture that compresses Chain-of-Thought (CoT) reasoning trajectories without Supervised Fine-Tuning (SFT). Evaluated on a strictly held-out TweetEval test set (N=734), RDS achieves 78.1% accuracy and a Macro F1 of 0.777, matching the absolute performance ceiling of the fine-tuned BERTweet. On the heavily imbalanced iSarcasm dataset, the frozen CoT pipeline filters 22.5% of out-of-distribution hallucinations, yielding a zero-shot Macro F1 of 0.6726 and Ironic F1 of 0.4821, outperforming multiple heavily supervised SemEval transformer ensembles. A statistical ablation confirms this structural synergy: adding the symbolic prior to the neural baseline yields no significant gain (p = 0.242), and the marginal benefit of adding the CoT pipeline to that prior is heavily compressed (p = 0.149). Only the complete, concurrent fusion of all three signals achieves a statistically validated improvement over the baseline (p = 0.005).

03.
arXiv (CS.CV) 2026-06-12

HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers

Holistic visual tokenizers are fundamental to unified multimodal models (UMMs) as they map diverse visual inputs into a unified representation space. In this paper, we present HYDRA-X, the first UMM that unifies image and video tokenization within a single Vision Transformer (ViT). Our design is driven by two core challenges: efficiently injecting spatiotemporal reconstruction capability into a native ViT, and embedding image- and video-level semantic awareness into the latent space. To address the first, comprehensive ablations reveal two key findings: (1) frame-level causal temporal attention suffices for visual reconstruction, whereas full spatiotemporal attention degrades it; and (2) hierarchical temporal compression substantially outperforms single-step alternatives. To tackle the second, we propose a lightweight decompressor that upsamples temporally compressed features under joint image-video teacher supervision, thereby enforcing complementary semantic structures within the compact latent space. Building on this holistic tokenizer, we further propose a principled improvement of the editing pipeline: source-target interaction should occur at the latent level inside the tokenizer rather than at the semantic level inside the LLM, substantially improving editing consistency and accelerating convergence. Instantiated at the 7B dense model, HYDRA-X achieves strong performance across image and video understanding and generation tasks, paving the way for future unified-tokenizer UMMs.

04.
arXiv (CS.AI) 2026-06-18

Surrogate Benchmarks for Model Merging Optimization

arXiv:2509.02555v2 Announce Type: replace-cross Abstract: Model merging techniques aim to integrate the abilities of multiple models into a single model. Most model merging techniques have hyperparameters, and their setting affects the performance of the merged model. Because several existing works show that tuning hyperparameters in model merging can enhance the merging outcome, developing hyperparameter optimization algorithms for model merging is a promising direction. However, its optimization process is computationally expensive, particularly in merging LLMs. In this work, we develop surrogate benchmarks for optimization of the merging hyperparameters to realize algorithm development and performance comparison at low cost. We define two search spaces and collect data samples to construct surrogate models to predict the performance of a merged model from a hyperparameter. We demonstrate that our benchmarks can predict the performance of merged models well and simulate optimization algorithm behaviors.

05.
arXiv (CS.AI) 2026-06-16

Towards End-to-End Automation of AI Research

arXiv:2606.15497v1 Announce Type: new Abstract: The automation of science is a long-standing ambition in the field of AI. While the community has made significant progress in automating individual components of the scientific process, a system that autonomously navigates the entire research lifecycle – from conception to publication – has remained out of reach. Here, we present the strongest demonstration to date toward automating the entire process end-to-end. We present The AI Scientist, which creates research ideas, writes code, runs experiments, plots and analyzes data, writes the entire scientific manuscript and performs its own peer review. Its ideas, execution, and presentation are of sufficient quality to produce a manuscript generated by an AI system that passes the first round of peer review at a major machine learning conference workshop. The workshop has an acceptance rate of 70 percent. Our system leverages modern foundation models within a complex agentic system. We evaluate The AI Scientist in two settings: a focused mode using human-provided code templates as an initial scaffold to conduct research on a specific topic, and a template-free, open-ended mode that leverages agentic search for wider scientific exploration. Both settings produce diverse ideas and automatically test, report on, and evaluate them. This achievement demonstrates AI's growing capacity for scientific contribution and signifies a potential paradigm shift in how research is conducted. As with any impactful new technology, there could be significant risks, including taxing overwhelmed review systems and adding noise to scientific literature. However, if developed responsibly, such autonomous systems could greatly accelerate scientific discovery.

06.
arXiv (CS.CL) 2026-06-11

Teaching Diffusion to Speculate Left-to-Right

Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their autoregressive decoding process incurs substantial inference costs due to inherently sequential token generation. Speculative decoding addresses this bottleneck by employing a lightweight draft model to propose multiple future tokens that are subsequently verified in parallel by a larger target model. Recent work has demonstrated that diffusion language models are well suited for this setting, as they can generate entire blocks of draft tokens in parallel and thereby alleviate the sequential constraints of autoregressive drafting. A subtlety of this regime is that block-diffusion drafters generate tokens bidirectionally within a block, whereas verification is performed by an autoregressive target model that evaluates tokens in a strictly left-to-right manner, leaving a gap between the symmetric training-time objective and the asymmetric verification-time reward. In this work, we offer an empirical analysis of three training-time interventions that narrow this gap: token positional weighting, a first-error focal loss that targets the position that breaks the accepted prefix within each block, and a chain loss term that substitutes a differentiable surrogate for the expected accepted length. The three interventions act along orthogonal axes (position, block-conditional first error, joint prefix) and compose additively; they are likewise orthogonal to test-time alignment mechanisms such as multi-draft self-selection, with which they can in principle be combined. Across four target models and six reasoning, code, and dialogue benchmarks, the three interventions raise accepted draft length by 21-76% per benchmark over a position-uniform baseline, without adding additional forward passes and without changing the inference pipeline or the rejection-sampling exactness contract.

08.
Nature (Science) 2026-06-10

Efficient and accurate neural-field reconstruction using resistive memory

作者:

Applications such as medical imaging, augmented and virtual reality, and embodied artificial intelligence (AI) depend on the ability to reconstruct complex signals from sparse observations. These applications are characterized by incomplete measurements and limited computational resources. Traditional approaches to digital hardware face the following challenges: explicit signal representations require heavy sampling and storage, data movement across the von Neumann bottleneck dominates energy and latency, and CMOS (complementary metal–oxide–semiconductor)-based circuits offer limited parallel efficiency. Here we present a software–hardware co-optimization framework for sparse-input signal reconstruction. At the software level, we use neural fields1 to implicitly represent signals using neural networks, which are further compressed by low-rank decomposition and structured pruning. At the hardware level, we design a resistive-memory-based computing-in-memory platform, featuring a Gaussian encoder and a multi-layer perceptron processing engine. The Gaussian encoder leverages the intrinsic stochasticity of resistive memory for efficient encoding, whereas the processing engine enables precise weight mapping through a hardware-aware quantization circuit. On a 40-nm 256 Kb resistive-memory macro, the system delivers 23.5×, 21.0× and 32.3× gains in projected energy efficiency, together with 10.8×, 38.8× and 6.2× gains in projected parallelism, for three-dimensional computed tomography sparse reconstruction, novel view synthesis and dynamic-scene novel view synthesis, without compromising on reconstruction quality. This work advances AI-driven signal reconstruction technology and paves the way for future efficient and robust medical AI and three-dimensional vision applications. A co-optimized AI hardware–software system using resistive-memory computing improves energy efficiency and parallelism for sparse signal reconstruction in imaging and three-dimensional vision applications.

09.
arXiv (CS.AI) 2026-06-17

Ensemble RL through Classifier Models: Enhancing Risk-Return Trade-offs in Trading Strategies

作者:

arXiv:2502.17518v3 Announce Type: replace-cross Abstract: This paper presents a comprehensive study on the use of ensemble Reinforcement Learning (RL) models in financial trading strategies, leveraging classifier models to enhance performance. By combining RL algorithms such as A2C, PPO, and SAC with traditional classifiers like Support Vector Machines (SVM), Decision Trees, and Logistic Regression, we investigate how different classifier groups can be integrated to improve risk-return trade-offs. The study evaluates the effectiveness of various ensemble methods, comparing them with individual RL models across key financial metrics, including Cumulative Returns, Sharpe Ratios (SR), Calmar Ratios, and Maximum Drawdown (MDD). Our original experimental results demonstrate that ensemble methods often outperform base models in terms of risk-adjusted returns, providing better management of drawdowns and overall stability. However, both the original analysis and the additional reproduction reported in this version show that ensemble performance is sensitive to the choice of variance threshold \(\tau\), classifier group, RL-agent pair, and market universe. The reproduction evidence strengthens the conclusion that classifier-assisted ensemble selection can improve robustness, while also clarifying that the advantage is conditional rather than automatic across all datasets. This study emphasizes the value of combining RL with classifiers for adaptive decision-making, with implications for financial trading, robotics, and other dynamic environments.

11.
arXiv (CS.CL) 2026-06-18

Enhancing Multilingual Reasoning via Steerable Model Merging

Model merging is an effective technique for composing the capabilities of a multilingual model and a reasoning model. It has achieved promising generalization in multilingual reasoning tasks by aligning feature spaces of different models. However, the merged single model often fails to address the conflicts between source models, leading to suboptimal performance. In other words, the one-size-fits-all merging strategy may not align with the characteristics of different inputs which may require prioritizing certain models over others. To this end, we propose a Steerable Model Merging (ST-Merge) framework to modulate the contribution of each source model. To realize this idea, we introduce a gated cross-attention mechanism to weight or filter the two attended source models in an adaptive manner. Extensive experiments demonstrate that ST-Merge consistently outperforms multiple strong baselines on four multilingual reasoning benchmarks across 21 different languages.

12.
arXiv (CS.LG) 2026-06-18

Sequential Hiring of Contingent Workers Through Learning-Based Optimization

arXiv:2606.18438v1 Announce Type: cross Abstract: In this paper, we study a sequential workforce management problem in a contingent labor setting with uncertainty in both worker production and labor supply. A firm seeks to maximize cumulative profit by maintaining an active team of fixed size while learning worker productivity over time. We emphasize two critical operational frictions in this problem: replacing workers is costly, and workers may not be available immediately for hiring because of, for example, prior job commitments, scheduling constraints, or onboarding procedures. Thus, hiring decisions take effect only after a random delay. We formulate this problem as a stochastic multi-play bandit with costly switching and delayed actions, and develop a learning-based hiring policy, DR-UCB (DelayedReplacement-UCB), that makes replacement and hiring decisions sequentially through learning cycles. In each cycle, the policy uses real-time production data to determine when to initiate workforce changes and which workers to replace and hire. We show that the leading-order regret of the proposed policy matches its lower bound in its dependence on the time horizon. Our numerical experiments show that DR-UCB outperforms benchmark policies.

13.
arXiv (CS.LG) 2026-06-15

A Complexity Measure for Active Learning in Multi-group Mean Estimation

arXiv:2606.14690v1 Announce Type: new Abstract: We study a max-risk objective for active learning in a multi-group mean estimation $d$-armed bandits: a learner adaptively allocates a budget of $T$ samples across $d$ groups to minimize the worst-case uncertainty index $\max_{k\in[d]}\sigma_k^2/n_k$, where $\sigma_k$ is the standard deviation of the distribution of arm $d$, and $n_k$ is the number of times arm $d$ is sampled. We develop a local minimax framework and prove the first general lower bound for this objective, valid for any finite-variance hypothesis class. The bound separates difficulty into three orthogonal factors: a budget term, a heteroscedasticity index measuring how unevenly the uncertainty is spread across arms, and a model-dependent complexity measure, the Variance Local Curvature ($\mathrm{VLC}$), which captures how much information a local change of variance creates inside the hypothesis class. For smooth classes, the $\mathrm{VLC}$ is a reparametrization of a variance–Fisher information, with closed-form values for common families. Benchmarking against the strongest available upper bound shows near-optimality up to logarithmic factors in broad regimes, and pinpoints a systematic gap in highly heterogeneous instances. Our proof introduces two key ingredients: a loss-induced $\ell_1$ geometry on the decision space, and a representation-based instance generator that reduces hard-instance construction to an explicit random matrix calculation.

15.
arXiv (CS.CL) 2026-06-11

The Long Tail, Not the Front Page: Cold-Start Prediction of Crowd Highlight Salience

A social highlighter's most useful signal – which passages a crowd of readers marks – exists only for documents people have already read. Can the aggregate crowd salience of a document be predicted from its text before its marks accumulate? Prior work on this data found that zero-shot language models recover highlight locations worse than a trivial lead (position) baseline, so we ask whether a model trained on the highlight corpus can beat that baseline. Using a pre-registered ladder of models and a by-document cluster bootstrap, we find a small but robust edge: a logistic ranker over sentence embeddings and positional/contextual features beats the lead baseline by +0.044 average precision (95% CI [+0.029, +0.058]; clears a pre-registered margin delta=0.03 in 97% of resamples, and stable across pipeline re-runs). Two unsupervised extractive baselines (centroid, LexRank-style centrality) lose to lead, and the trained model beats them by +0.108, so the edge is not recovered by generic unsupervised proxies – it reflects learning from real reader marks. In product terms, precision@3 rises from 0.25 to 0.39 (+55% relative) and the model beats lead on 69% of documents. An ablation attributes the edge to the raw embedding (+0.014) and training augmentation (+0.010), each with a positive CI. The edge is not a temporal-generalization failure, and we find no evidence that content drift or near-duplicate leakage explains it. A standardized regression shows the advantage is governed mainly by document popularity (lower popularity, larger edge) and by label reliability. It nearly vanishes only on the most popular content; there it is the lead baseline that strengthens, not the model that weakens. Because our evaluation conditions on documents that eventually accumulated readers, these results are a retrospective cold-start simulation.

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

Natural-Language Temporal Grounding in Hour-Long Videos is a Search Problem: A Benchmark and Empirical Decomposition

Temporal grounding–returning the interval $[t_s, t_e]$ for a natural-language query over a video–is the language interface to long-form video, yet has been studied on short videos; the dynamics of hour-scale natural-language grounding remain underexplored. We take the position that at hour-scale, the binding constraint is search, not recognition: Video-LLMs are bottlenecked not by localizing a nearby event, but–given a natural-language query–by searching for the relevant region of a long video. To test this, we release ExtremeWhenBench, the first open hour-scale grounding benchmark (2,273 queries over 194 videos, mean 75.7 min, max 9 hr) with an open-form query distribution. Every open Video-LLM collapses while a frame-level retrieval baseline outperforms them; a failure taxonomy attributes 85% of failures to search; and a retrieve-then-ground hybrid recovers 6.7x over the monolithic Video-LLM–mirroring retrieve-then-read in open-domain QA.

17.
arXiv (CS.LG) 2026-06-17

CheckMIABench: Firm Foundations For Membership Inference Attacks on Language Models

arXiv:2606.17464v1 Announce Type: new Abstract: Membership inference attacks (MIAs) are a canonical way to assess a machine learning model's privacy properties. Although several attempts have been made to evaluate MIAs on language models, the extant literature has suffered numerous difficulties in constructing clean evaluations to test new techniques. In particular, subtle distribution shifts between member and non-member sets can undermine the statistical validity of MIAs; recent work has underscored this by showing that "blind" methods with no access to the underlying model can perform far better than published methods on the same benchmarks. This paper constructs a benchmark for principled evaluation of MIAs against LLMs, by leveraging the insight that training data before and after a fixed point during training are drawn from the same distribution. Therefore, all open-source models with intermediate checkpoints and public training data can be converted into MIA testbeds. We apply our framework to a half-dozen published attacks on the Pythia and OLMo family of models, from 70M to 7B parameters. To facilitate further privacy research, we open-source a modular library for designing and implementing attacks in this setting: https://github.com/safr-ai-lab/pandora_llm.

18.
arXiv (quant-ph) 2026-06-16

Gaussian superpositions for bosonic encodings

arXiv:2603.15258v2 Announce Type: replace Abstract: Non-Gaussian bosonic states are ubiquitous in interacting light–matter systems, many-body platforms, and relativistic quantum field settings, but their quantitative characterization is hindered by the infinite-dimensional Hilbert space and by the poor scalability of Fock-space truncation methods. We introduce an exact finite-manifold encoding for states supported on a finite span of Gaussian branches, enabling the use of standard finite-dimensional quantum-information tools directly on an effective density matrix whose entries are determined by Gaussian overlaps. As demonstrations, we obtain closed-form and numerically stable evaluations of entropies and relative-entropy non-Gaussianity, and derive an analytic expression for the bipartite entanglement negativity of arbitrary multimode two-branch Gaussian superpositions, including a minimal which-branch dephasing model. Our framework provides a practical bridge between experimentally accessible continuous-variable resources (e.g., cat-like and measurement-conditioned states) and discrete-variable information measures, with immediate applications to benchmarking non-Gaussian resources in several quantum technology platforms.

19.
bioRxiv (Bioinfo) 2026-06-11

A high-quality chromosome-scale reference genome assembly for Asparagus racemosus var. CIM-Shakti (Shatavari), a medicinal plant of Ayurvedic importance

Asparagus racemosus Wild., commonly known as Shatavari, is an important medicinal plant in Ayurveda and is valued for its steroidal saponins, particularly shatavarin compounds, which contribute to its adaptogenic, galactagogue, immunomodulatory, and therapeutic properties. Despite its medicinal and economic importance, genomic resources for this species have remained limited, restricting molecular breeding, pathway discovery, and comparative evolutionary studies within Asparagaceae. Here, we report a high quality chromosome scale reference genome assembly of A. racemosus var. CIM Shakti generated using PacBio HiFi long read sequencing and Omni C chromatin conformation scaffolding. The pseudo haploid assembly spans 817 Mb across 53 scaffolds, with a scaffold N50 of 98.50 Mb, L50 of 5, and a largest scaffold of 113.80 Mb. Ten major chromosome scale pseudomolecules were resolved, corresponding to the haploid chromosome complement of A. racemosus. The assembly showed high gene space completeness, with BUSCO completeness of 99.8% against the Eukaryota dataset and 98.0% against the Embryophyta dataset. BlobToolKit profiling further supported assembly quality, with GC content of approximately 39 to 40% and no major evidence of contamination. EDTA based repeat annotation identified 580.93 Mb of interspersed repetitive elements, accounting for 71.06% of the 817.57 Mb genome assembly. The repeat landscape was dominated by LTR retrotransposons, particularly Gypsy elements, which accounted for 25.01% of the assembly, followed by unclassified LTR elements at 26.58% and Copia elements at 4.84%. Structural and functional annotation identified 29,199 protein coding genes represented by 29,199 transcript models, 138,433 exons, and 125,201 CDS features. The annotation was structurally robust, with an average gene length of 4,605.1 bp, 4.74 exons per transcript, and 97.80% of transcripts containing multiple exons. The CIM Shakti reference genome provides a foundational genomic resource for investigating steroidal saponin biosynthesis, sex chromosome evolution, repeat driven genome expansion, and comparative genomics in Asparagaceae. This assembly will support future studies on medicinal trait improvement, conservation genomics, and genomics assisted breeding of climate resilient Shatavari cultivars.

20.
medRxiv (Medicine) 2026-06-22

A blinded, counterbalanced rater design for evaluating AI-assisted summarisation of tertiary clinical genomics reports: methodology of the QNOMX-VHIR-CPSP-001 Phase 1 study

Background. Tertiary clinical genomics reports condense layered molecular findings into documents that treating oncologists must read, translate, and act upon; manual summarisation of these reports is time-consuming and variable. Tools that assist summarisation and translation into local languages are emerging, yet the field lacks an agreed methodology for evaluating such tools before any downstream clinical use. The appropriate first endpoint is fidelity of the generated summary to its source report, assessed by qualified human raters under blinded scoring, not downstream variant classification. Methods. QNOMX-VHIR-CPSP-001 Phase 1 is a single-site, non-interventional clinical performance study conducted at Vall d'Hebron Institut de Recerca (VHIR) under ISO 20916:2019 as a Clinical Performance Study Protocol. De-identified tertiary cancer genomics reports from pediatric oncology cases are summarised by the AI-assisted summarisation system under evaluation and, in parallel, by the standard manual workflow. Qualified raters score both summary types against the source genomics report using the Quality Summary Index (QSI), a six-dimension, five-point rubric adapted from the Provider Documentation Summarization Quality Instrument, under a blinded, counterbalanced, two-period crossover with a minimum fourteen-day washout. Two co-primary composite endpoints, content and presentation, are analysed for non-inferiority under a Bayesian hierarchical model, with a frequentist linear mixed model as the convergence check. Inter-rater reliability is reported as Krippendorff's ; a Monte-Carlo power analysis of the fixed clustered design is pre-specified. Discussion. The design isolates summarisation quality from clinical decision-making by scoring both summary types against the same source report under blinding, counterbalancing, and a fourteen-day washout. Conclusion. The QSI rubric, the counterbalanced crossover, and the pre-specified Bayesian primary with frequentist convergence check define a replicable protocol for early-stage evaluation of AI-assisted summarisation in tertiary genomics reporting; observed variance components will inform sample-size determination for Phase 2.

21.
arXiv (CS.LG) 2026-06-11

LakeFM: Toward a Foundation Model for Aquatic Ecosystems Using Irregular Multivariate Multi-depth Time Series Data

arXiv:2606.11268v1 Announce Type: new Abstract: Understanding and forecasting lake dynamics is critical for monitoring water quality and ecosystem health across lakes and reservoirs. While machine learning methods have been recently applied to ecological time-series data, existing works assume regular sampling in time and depth, and struggle to generalize across lakes with heterogeneous variables, depths, and observation patterns. To address these limitations, we introduce \textsc{LakeFM}, a foundation model for aquatic systems, pre-trained on large-scale ecological datasets comprising both simulated and observed lakes. Through extensive empirical evaluation, we show that \textsc{LakeFM} learns meaningful representations spanning broader lake-level characteristics, and achieves competitive or often superior-forecasting performance compared to existing time-series foundation and non-foundation models, while producing physically plausible predictions consistent with real-world lake dynamics.

22.
arXiv (CS.CL) 2026-06-11

ALIGNBEAM : Inference-Time Alignment Transfer via Cross-Vocabulary Logit Mixing

Domain fine-tuning degrades the safety of large language models: fine-tuned specialists readily comply with harmful prompts framed in domain language. Existing inference-time defenses that mix logits from a safe anchor model require both models to share a vocabulary, which rules them out for the cross-family specialists where safety is most degraded. We present ALIGNBEAM, a training-free method that lifts this restriction by translating anchor logits into the target model's vocabulary token-by-token at each decoding step; a small LLM judge then selects the safest among K candidate continuations. No weights are changed, and the safety-utility trade-off can be tuned at deployment without retraining. Across both cross-vocabulary and same-vocabulary evaluation pairs, ALIGNBEAM substantially raises refusal on adversarial benchmarks while keeping task accuracy and inference overhead within practical bounds. The results show that safety alignment can be transferred between model families at inference time, without touching either model's weights.

23.
arXiv (CS.CL) 2026-06-12

A Unifying Lens on Reward Uncertainty in RLHF

Reinforcement learning from human feedback (RLHF) is bottlenecked by reward hacking, where the policy exploits errors in a proxy reward model (RM) and produces high RM scores without genuine quality gains. A natural mitigation is pessimism: lowering rewards in regions where the RM is uncertain. However, standard scalar RMs provide no principled notion of uncertainty. We argue that the right object is a distributional reward model $p(r\mid x,y)$. Under either a Bayesian inference or a KL-distributionally robust optimization (KL-DRO) lens, the KL-regularized RLHF objective admits a closed-form effective reward $\tilde r(x,y) = \pm\beta\log\mathbb{E}_p[e^{\pm r/\beta}]$. The pessimistic branch unifies the prior heuristics for RM ensemble aggregation: mean aggregation, worst-case optimization (WCO), and uncertainty-weighted optimization (UWO) all emerge as limits or truncations of this single expression. This also clarifies the implicit assumptions of each existing rule.

24.
arXiv (CS.AI) 2026-06-11

CCKS: Consensus-based Communication and Knowledge Sharing

arXiv:2606.12281v1 Announce Type: cross Abstract: In Decentralized Training and Decentralized Execution (DTDE) for cooperative Multi-Agent Reinforcement Learning (MARL), action-advising-based knowledge sharing promotes interpretable and scalable cooperation among agents. However, current action advising approaches often adhere too much to the teacher's guidance without evaluating teacher-student compatibility, which causes excessive advising, suboptimal stability, and degraded performance. To overcome these challenges, this paper presents a Consensus-based Communication and Knowledge Sharing (CCKS) framework, which allows agents to adopt recommendations based on consensus-derived constraints and to follow the teacher's instructions more smartly. This mechanism enables agents to balance exploration and learning from experienced teachers, improving overall performance. The key is the consensus model construction, for which we propose to employ contrastive learning to construct consensus models based on local observations in the agents' training phase. In action selection, agents score and choose actions based on consensus and shared knowledge. Designed as a plug-and-play solution, CCKS integrates seamlessly with existing DTDE algorithms. Experiments conducted in the Google Research Football environment and the complex StarCraft II Multi-Agent Challenge demonstrate that the integration with CCKS significantly improves cooperation efficiency, learning speed, and overall performance compared with current DTDE baselines. The code is available at https://github.com/yuanxpy/CCKS.

25.
arXiv (CS.CV) 2026-06-16

RGFVR: Reference-Guided Face Video Restoration with Flow Matching

Face video restoration from degraded observations is challenging, as it requires simultaneously recovering visual fidelity, temporal consistency, and subject identity. Existing approaches are often either reference-free, which can lead to identity loss when person-specific facial details are lost, or subject-specific, which limits generalization to unseen identities. We propose a subject-agnostic, reference-guided framework for identity-preserving face video restoration. Our method introduces bimodal perceptual-descriptive identity conditioning into a pretrained flow-based text-to-video generator and employs a two-stage training strategy to strengthen identity guidance during restoration. Experiments show that our approach improves restoration fidelity, temporal consistency, and identity preservation, achieving superior performance under challenging video degradations, including downsampling, blur, noise, and compression artifacts. The code is available under: https://github.com/batuhanntosun/RG-FVR.