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.CL) 2026-06-15

The Linguistics Olympiads: Towards a New Corpus for Linguistics Research?

Linguistics olympiad problems (LOPs) are a category of self-sufficient puzzles consisting of a scaled-down corpus representative of certain linguistic phenomena, from which the solver must deduce a primitive set of rules of the language and then translate a new set of elements. The linguistics olympiads (LOs) have become a worldwide phenomenon with 43 different territories taking part in the International Linguistics Olympiad (IOL) 2025. While the typology and solving strategies of LOPs have been analysed, their scientific facet and connections to academic linguistics have yet to be explored. LOPs are directly connected to many linguistic fields, e.g., linguistic typology, linguistic relativity, and linguistics fieldwork. Recently, LOPs have become a research focus as benchmarks for large language models, thus highlighting their usefulness in computational linguistics. Nevertheless, they have not yet been integrated into mainstream linguistics research. This paper attempts to open new directions of including this particular type of puzzle in academic research by offering a structured evaluation of LOPs as linguistic data sources and proposes criteria for their responsible use in academic research. Starting from a set of over 1800 LOPs, this study critically examines the potential of LOPs as a novel corpus for linguistics research by discussing their strengths and limitations as tools, as well as the areas of linguistics into which these problems could fit. This work forms the foundation for a broader initiative aimed at bridging the gap between LOs and academic linguistics, by establishing a robust theoretical framework for LOPs.

02.
medRxiv (Medicine) 2026-06-15

Primary care practitioners preconception health literacy and information-seeking: A cross-sectional survey.

Background Parental health before pregnancy influences maternal and child outcomes. Primary care professionals, including general practitioners [GPs], midwives, and naturopaths, can provide preconception care, yet many report limited knowledge and difficulty accessing relevant information. This study described Australian GPs, midwives, and naturopaths preconception health literacy, including knowledge and ability to access information. Methods Between July and September 2022, Australian GPs, midwives, and naturopaths completed a 32-item online cross-sectional survey. Participants were recruited through professional associations, and data were analysed using descriptive and inferential statistics Results Participants (N=373) included naturopaths (40.7%), GPs (32.4%), and midwives (26.8%). Reported barriers to clinician health literacy including lack of preconception care resources (25.5%), and limited clinician knowledge (23.6%). The proportion identifying limited clinician knowledge differed significantly between professions (GP: 31.4%; midwives: 23.0%; naturopaths: 17.8%; p=0.030). The highest level of accurate knowledge regarding preconception exposures was for pre-pregnancy obesity (82.7%), while low birth weight was the most accurately identified preconception outcomes (83.7%). Incorrect responses were most common for maternal multivitamin use as an exposure (28.3%) and childhood leukaemia as an outcome (26.3%). Differences between professions were strongest for infant outcomes, with moderate associations observed for shoulder dystocia (V=.2355), precipitous labour (V=.2173), macrosomia (V=.2060), labour dystocia (V=.2018) and cryptorchidism (V=.2018). Discussion Preconception health literacy varies across primary care professions. Clinicians require greater access to targeted resources and education tailored to their differing scopes of practice and experience. Improving clinician preconception health literacy may strengthen consistent evidence-based care and support better maternal, child, and long-term family health outcomes.

03.
arXiv (CS.LG) 2026-06-11

Trajectory Geometry of Transformer Representations Across Layers

arXiv:2606.09287v2 Announce Type: replace Abstract: Understanding how transformer representations evolve across layers, not merely what they encode, remains an open problem in mechanistic interpretability. We recast the transformer forward pass as a discrete population trajectory through a high-dimensional representation manifold, drawing on geometric tools from computational neuroscience. Rather than probing for pre-specified features, we characterize trajectory geometry using five metrics computed directly in the ambient space: trajectory length, curvature, a semantic convergence index, layerwise cosine similarity, and representational stability. Across three model families (GPT-2, TinyLlama, Qwen2.5) and five controlled prompt families, we report four findings. First, semantically related prompts converge significantly in middle-to-late layers (peak CI 0.41–0.58, p

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

Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models

arXiv:2605.31158v3 Announce Type: replace-cross Abstract: Interactive video world models generate video chunk by chunk in response to user-controlled camera movements, enabling applications such as real-time game simulation, virtual scene navigation, and embodied AI training. However, scaling to long interactive trajectories is prohibitively expensive due to growing context memory, quadratic attention complexity, and repeated denoising steps. We present Light Interaction, a training-free inference acceleration framework for interactive video world models. Our key insight is that interaction naturally enables trajectory-dependent adaptive computation: retrieved spatial memory can be discarded during novel exploration, temporal context can be adjusted according to local latent dynamics, and early-step model outputs can be reused when the camera revisits familiar regions. Based on this insight, Light Interaction combines adaptive context management, denoising cache acceleration, and hardware-software co-designed 3D block sparse attention with fused Triton kernels. Evaluated on HY-WorldPlay and Matrix-Game-3.0, Light Interaction achieves up to 2.59x speedup without model retraining while maintaining competitive visual quality.

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

RaBiT: Residual-Aware Binarization Training for Accurate and Efficient LLMs

arXiv:2602.05367v3 Announce Type: replace Abstract: Efficient deployment of large language models (LLMs) requires extreme quantization, forcing a critical trade-off between low-bit efficiency and performance. Residual binarization enables hardware-friendly, matmul-free inference by stacking binary ($\pm$1) layers, but is plagued by pathological feature co-adaptation. We identify a key failure mode, which we term inter-path adaptation: during quantization-aware training (QAT), parallel residual binary paths learn redundant features, degrading the error-compensation structure and limiting the expressive capacity of the model. While prior work relies on heuristic workarounds (e.g., path freezing) that constrain the solution space, we propose RaBiT, a novel quantization framework that resolves co-adaptation by algorithmically enforcing a residual hierarchy. Its core mechanism sequentially derives each binary path from a single shared full-precision weight, which ensures that every path corrects the error of the preceding one. This process is stabilized by a robust initialization that prioritizes functional preservation over mere weight approximation. RaBiT redefines the 2-bit accuracy-efficiency frontier: it achieves state-of-the-art performance, rivals even hardware-intensive Vector Quantization (VQ) methods, and delivers a $4.49\times$ inference speed-up over full-precision models on an RTX 4090. Code is available at https://github.com/SamsungLabs/RaBiT.

06.
arXiv (math.PR) 2026-06-11

On Skorokhod Problems for Reflected and Singular Stochastic Heat Equations

arXiv:2606.11951v1 Announce Type: new Abstract: We prove a Skorokhod decomposition for the Markov processes $X^a$ and $X$ associated to the gradient Dirichlet forms with respect to the measures $\rho^a\mu^{\beta}$ and $\rho\mu^{\beta}$, respectively. Here, $\mu^{\beta}$ is the law of the standard Brownian bridge $\beta$, while $\rho^a$ and $\rho$ denote densities which are given by $\rho^a(z) := \mathbf{1}_{[0,\infty)}(\bar{z}_a)$ and $\rho(z) := \int_0^1 \mathbf{1}_{[0,\infty)}(\bar{z}_x) \, dx$, respectively, for all $z\in L^2(0,1)$ which have a (unique) continuous representative $\bar{z}$ which vanishes at zero and one. To this end, we derive infinite-dimensional integration by parts formulas (IbPFs) w.r.t. $\rho^a\mu^{\beta}$ and $\rho\mu^{\beta}$, which contain Hida distributions alongside the usual drift terms. We represent these Hida distributions by integration w.r.t. vector measures of bounded variation. The vector measures in question are constructed via an approximation argument, making use of a generalization of Prokhorov's theorem for vector measures. We further prove that, almost surely, the sample paths of $X^a$ and $X$ take values in the equivalence class of continuous functions vanishing at zero and one for all and $dt$-almost all times, respectively. The main motivation for studying $\rho^a\mu^{\beta}$ and $\rho\mu^{\beta}$ lies in the fact that the distributional terms in their IbPFs are simplifications of the distributional term in the IbPF w.r.t. the law of the reflected Brownian bridge on the unit interval $\mu^{|\beta|}$. Representing the latter by integration w.r.t. a vector measure of bounded variation is still an open problem.

07.
arXiv (quant-ph) 2026-06-19

Computing noise-canceling observables via Pauli propagation

arXiv:2606.20441v1 Announce Type: new Abstract: The pursuit of quantum advantage is driving the co-evolution of quantum processors and classical simulation methods. Despite advances in scale and quality, the accuracy of quantum simulation is ultimately limited by error rates and sampling overheads. Similarly, while classical simulation methods such as Pauli propagation have made remarkable progress, their accuracy is ultimately limited by the exponential growth of operator paths and the truncations needed to control memory and runtime. Here we show that these complementary limitations can be mitigated by embedding Pauli propagation within a hybrid error-mitigation framework that reduces quantum sampling overhead while achieving lower truncation errors with fewer classical resources than traditional Pauli propagation alone. In this framework, a target observable is classically propagated through noise-canceling inverse channels, producing a modified observable that is measured directly on a quantum processor. We prototype two implementations and benchmark their performance numerically on canonical models that challenge traditional Pauli propagation. We also perform experiments on a quantum processor using 56 superconducting qubits, revealing the tradeoffs of their respective truncation strategies. These results illustrate how classical and quantum resources can be orchestrated to extend observable estimation beyond the limits of either approach alone, providing a foundation for quantum-centric supercomputing and future demonstrations of quantum advantage.

08.
arXiv (CS.AI) 2026-06-15

When Should Agent Trust Be Conditional? Characterizing and Attacking Skill-Conditional Reputation in Agent Swarms

arXiv:2606.14200v1 Announce Type: new Abstract: Open platforms increasingly route tasks among heterogeneous LLM agents–differing in base model, scaffold, and tool stack–whose competence varies sharply by skill: an agent excellent at one skill may be useless at another. The standard reputation approach summarizes each agent by a single global trust score, but that scalar is the wrong object here, because routing every task to the globally most-trusted agent leaves the value of specialization unclaimed. We study skill-conditional trust R(i | k)–the trust to place in agent i for a task requiring skill k, rather than one score per agent–and pose three falsifiable questions: when is conditioning worth it, how much cross-skill evidence should be borrowed, and whether that borrowing is safe. A controlled phase-diagram analysis answers the first two: conditional trust wins only in a specific regime–high agent heterogeneity, sparse per-skill evidence, and correlated skills–and the coupling strength beta that buys this data efficiency is dual-use, because the same cross-skill borrowing is also a laundering channel. On a public benchmark of 14 genuinely heterogeneous AppWorld agents, real pools land inside the beneficial regime–a small but genuine gain, with the per-skill best agent genuinely changing across skills. We then show that an attacker with cheap evidence in one skill and none in a target skill hijacks the conditional router, driving routing regret from 0 to 0.94 on a pool our zero-cost Conditional Information Value Test (CIVT) rates GREEN–while the ungated trust verdict it contaminates reads -0.06 instead of the honest +0.19. A zero-evidence gate bounds the attack but does not eliminate it; we characterize the residual cost under an explicit budget. We do not claim Sybil-resistance–we quantify the trade-off.

09.
arXiv (quant-ph) 2026-06-15

Local correlations in long-range dual-unitary kicked Hamiltonian chains

arXiv:2606.13857v1 Announce Type: new Abstract: Many-body Floquet models with exact space–time symmetry, such as the kicked Ising spin chain (KIC), provide natural examples of systems with dual-unitary dynamics. The requirement of exact space–time symmetry is, however, highly restrictive, as it permits only nearest-neighbor interactions. Based on a pair of Hadamard matrices, we construct a wide family of dual-unitary kicked spin chains with long-range interactions. We show that local two-point correlations in such models propagate along the light-cone edges \( |n| = r|t| \), where \(r\) is the interaction range, and can be derived analytically for operators with local support. This approach is illustrated using the example of a kicked Ising spin chain with next-to-next-neighbor interactions.

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

Towards Interpretability of Neural Quantum States

arXiv:2508.14152v2 Announce Type: replace Abstract: Neural quantum states (NQS) have emerged as a powerful variational ansatz for representing quantum many-body wave functions. Their internal mechanisms, however, remain poorly understood. We investigate the role of correlations for NQS-like quantum state representation by employing a correlation-based interpretable neural network architecture and then proving our observations using Boolean function theory. The correlator neural network demonstrates that, even for simple product states, up to all system-size correlation orders in the chosen computational basis are required to represent a quantum state faithfully. We explain these observations using Fourier expansion, which reveals the correlator basis as the effective basis of the internal NQS structure, the resulting necessity for high-order correlations that is supported by an entanglement bound that scales with the correlation order, consequences of linear dependencies in constrained Hilbert spaces for correlation requirements, and connections between spin basis rotations and the correlator basis. Furthermore, we analyze how neural networks achieve high correlation orders by increasing the magnitude of the network weights, which can be compensated by increasing the network depth. Lastly, we discuss how activation functions, network architectures, and choice of reference basis influence correlation requirements. Our results provide new insights and a better understanding of the internal structure and requirements of NQS, enabling a more systematic use of NQS in future research.

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

Multi-Turn Reflective Masking Elicits Reasoning in Mask Diffusion Models

While reasoning on autoregressive (AR) models is often performed by chain-of-thought reasoning and reflection, their refinement of previous outputs still relies on fully sequential generation, even when only local edits are needed. In contrast, the masking mechanism in Mask Diffusion Models (MDMs) naturally supports explicit local edits on previous outputs, allowing selective refinement without discarding previous answers and generating another from scratch. While this property more closely aligns with how humans correct mistakes by iterative local refinement, existing MDMs do not support multi-turn masking and denoising. We propose Reflective Masking (RM), which elicits such an intrinsic reasoning capability in MDMs via lightweight post-training. RM provides a native test-time scaling, where an MDM iteratively revisits and revises its prior outputs based on evolving context. To exploit insights from previous turns like AR reasoning, we further introduce History Reference, a parameter-free mechanism that leverages intermediate denoising states during revision. Our approach requires no architectural changes and is easily applicable to existing MDMs. Across diverse tasks and modalities, including text generation, Sudoku, and image editing, Reflective Masking consistently outperforms standard masking-based baselines and demonstrates strong generality, positioning RM as a fundamental primitive for reasoning on MDMs.

12.
arXiv (CS.CL) 2026-06-16

P3B3: A Multi-Turn Conversational Benchmark for Measuring European and Brazilian Portuguese Variety Bias in LLMs

As Large Language Models (LLMs) become embedded in everyday communication, capturing regional linguistic variation is essential for reliable and equitable language use. In Portuguese, European (pt-PT) and Brazilian (pt-BR) varieties remain unevenly represented, with pt-BR dominating in data quantity, while LLM preference for Portuguese variants remains underexplored. To address this gap, we introduce P3B3, an expert-curated language variety agnostic benchmark of conversational prompts, along with an evaluation framework for measuring variety bias and controllability. Experiments on several models show that most LLMs exhibit a strong bias toward pt-BR, with variation in controllability across models. These results highlight the need for more balanced multilingual representation across language varieties.

13.
medRxiv (Medicine) 2026-06-15

Dysplasia-Stratified Management of Barrett's Esophagus: An Incidence-Based U.S. Cost-Effectiveness Analysis

作者:

Background and Aims Barrett's esophagus (BE) is the principal precursor of esophageal adenocarcinoma (EAC), whose incidence has risen sharply in Western countries since the 1960s. Effective, dysplasia stratified surveillance strategies are needed to prevent progression. This study evaluated the cost effectiveness of dysplasia stratified surveillance intervals and endoscopic eradication therapy (EET) across the BE spectrum. Methods We developed an incidence-based Markov state transition model of BE progression calibrated to U.S. epidemiologic data from a healthcare sector perspective over a lifetime horizon. Four hypothetical cohorts of 50-year-old individuals with short segment BE (SSBE), nondysplastic BE (NDBE), low grade dysplasia (LGD), or high-grade dysplasia (HGD) were evaluated. Strategies included no surveillance; surveillance at 1-, 2-, 3-, 4-, 5-, or 10-year intervals; standard or AI assisted endoscopy; non endoscopic screening (sponge, breath, miRNA tests); and EET for LGD and HGD. Outcomes included costs, quality adjusted life years (QALYs), incremental cost effectiveness ratios (ICERs), net monetary benefits (NMBs), EAC cases, and EAC-related deaths. Sensitivity analyses used a willingness to pay threshold of US$100,000 per QALY. Results No surveillance was the most cost-effective strategy for SSBE and NDBE. For LGD, upfront EET was more cost effective than all surveillance strategies, with results sensitive to EAC incidence and recurrence. For HGD, EET was cost saving and yielded the greatest QALYs, with findings robust in 99.9% of simulations. EET prevented 12,614 and 44,295 EAC related deaths per 100,000 individuals with LGD and HGD, respectively. Conclusion Dysplasia-stratified management is essential for optimizing surveillance and treatment strategies in BE. Any degree of dysplasia should receive EET followed by targeted post-treatment monitoring, establishing EET as the central therapeutic pathway for dysplastic BE.

14.
arXiv (CS.CL) 2026-06-16

KVEraser: Learning to Steer KV Cache for Efficient Localized Context Erasing

Post-hoc context erasing over the KV cache is challenging because a local edit has a global consequence: once a span has been processed, its influence propagates into the cached states of all subsequent tokens. This issue arises naturally in long-context LLM applications, where stale retrieved facts, incorrect tool observations, retracted user preferences, or harmful prompt injections may be identified only after prefill. Exact erasing must then recompute all tokens after the deleted span, making its computational cost depend on suffix length rather than erased-span length. We introduce KVEraser, a learned KV-cache editing method for efficient localized context erasing. Given a processed context and a span to remove, KVEraser replaces only the KV states of the erased interval with learned steering states while reusing the remaining cache unchanged. To learn a transferable erasing mechanism, we build a two-stage training pipeline: generic span-neighbor pre-training teaches the eraser to suppress the influence of the erased span, while task-specific fine-tuning adapts this capability to downstream scenarios. Experiments show that KVEraser nearly matches full recomputation in post-erasure performance on in-domain tasks across 1K–32K context lengths, while its latency increases by only 24% compared with a 17.6x increase for full recomputation. KVEraser also generalizes to unseen long-document QA tasks with harmful factual distractors, achieving the best performance among approximate baselines with a 3–4x speedup over full recomputation.

15.
arXiv (CS.LG) 2026-06-18

Gaussian Mixture Attention: Linear-Time Sequence Mixing via Probabilistic Latent Routing

arXiv:2606.18283v1 Announce Type: new Abstract: The dense token-to-token interaction pattern of standard dot-product attention remains a central bottleneck in scaling Transformer architectures to long contexts. We introduce Gaussian Mixture Attention (GMA), a probabilistic attention-style sequence mixer that replaces explicit pairwise query–key comparison with routing through $K$ learned Gaussian mixture components. Queries and keys are mapped to posterior responsibility vectors over a shared latent routing space; their overlap defines an implicit responsibility-space affinity, while values are written into and read from a $K$-slot latent memory. By exploiting the associativity of matrix multiplication, GMA avoids materializing the induced $N\times N$ affinity matrix and instead uses two responsibility matrices whose dominant activation storage scales as $\mathcal{O}(NK)$ rather than $\mathcal{O}(N^2)$ for fixed $K$. We formulate bidirectional and causal variants of GMA, provide an end-to-end differentiable parameterization of the Gaussian mixture components, and analyze its responsibility-modulated gradient structure, constrained non-negative low-rank affinity interpretation, and local routing stability. Empirically, GMA exhibits the intended fixed-$K$ linear memory scaling and is competitive with attention-style baselines on long-context classification, while causal GMA improves over tested linear/random-feature attention variants on WikiText-103 but remains behind optimized causal SDPA and Mamba in the current implementation. Analysis of learned responsibilities further shows broad component usage and moderate alignment with surface-form token categories, supporting GMA as a probabilistic, interpretable, fixed-$K$ linear-time attention-style alternative rather than a universal replacement for optimized softmax attention or state-space models.

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

MIRAGE: Auditing Anti-Muslim Bias in Frontier LLMs Across Reasoning, Agentic, and Time-Coupled Conditions

arXiv:2606.16562v1 Announce Type: new Abstract: Five years after the discovery of persistent anti-Muslim bias in large language models, most evaluations remain confined to single-turn prompt completion, a setting that no longer reflects how frontier LLMs are deployed. We introduce MIRAGE (Muslim-Identity Reasoning and Agentic Generation Evaluation), a benchmark of 1{,}200 prompts spanning three deployment-realistic conditions: direct completion, chain-of-thought reasoning, and simulated agentic decision-making across content moderation, lending triage, refugee claim summarization, and hiring screens. Across six frontier models, we find that (i) chain-of-thought reasoning amplifies rather than suppresses Muslim-violence associations by 12–34\% relative to direct completion, (ii) agentic decisions exhibit a 9–22 percentage-point asymmetry between Muslim and matched non-Muslim cases on identical evidence, and (iii) bias is sharply time-coupled to retrieved news context, increasing 18–27\% under recent-conflict retrieval. Existing prompt-based mitigations transfer poorly across our three conditions, suppressing direct-completion bias while leaving agentic asymmetry largely intact. We release MIRAGE and an open evaluation harness to support targeted mitigation research.

17.
arXiv (CS.CL) 2026-06-19

MENTOR: Reinforcement Learning via Flexible Teacher-Optimized Rewards for Tool-Use Distillation

Distilling the tool-use capabilities of large language models (LLMs) into small language models (SLMs) is essential for their practical application. The predominant approach, supervised fine-tuning (SFT), suffers from poor out-of-domain (OOD) generalization due to its rigid alignment with static teacher trajectories. While reinforcement learning (RL) offers an alternative, the capacity limitations of SLMs pose a severe dilemma: sparse outcome rewards provide insufficient guidance, whereas strict trajectory matching imposes overly restrictive constraints. To bridge this capacity-driven gap, we propose MENTOR, which introduces a flexible yet process-aware reward structure. Instead of enforcing rigid replication, MENTOR uses the teacher's reference to guide tool-use behavior, balancing behavioral alignment with downstream performance. Extensive experiments on controlled executable-tool benchmarks demonstrate that MENTOR improves OOD tool-use performance compared to SFT and strict RL baselines. Our findings suggest that within verifiable tool-use environments, flexible tool-use alignment offers a more effective approach than strict trajectory replication for developing adaptable small models.

18.
arXiv (quant-ph) 2026-06-17

Impact of Network Constraints on Fault-Tolerant Distributed Quantum Computing

arXiv:2606.17495v1 Announce Type: new Abstract: As we move towards scalable and modular quantum computing, quantum data centres become imperative. Existing analyses typically treat network constraints in isolation or through simplified models, leaving the interplay between error correction operations and communication resources underexplored. In this work, we present an end-to-end simulation framework that jointly models surface-code operations, internal QPU connectivity, and realistic network constraints including finite entanglement generation rates, limited communication qubits, and bandwidth contention, producing execution latency, from which logical error rate estimates are obtained. The framework is modular by design, allowing individual components such as routing heuristics, scheduling policies, and network topologies to be independently replaced. Numerical evaluation reveals distinct operating regimes in which the optimal resource allocation and code distance selection shift depending on the network characteristics. These results point to tradeoffs in the design of distributed quantum computing architectures that are not visible when computation and communication are modeled separately.

19.
arXiv (CS.LG) 2026-06-17

AoiZora: Topology-Aware Auto-Parallel Optimization for Inference of Diffusion Transformers

arXiv:2606.17566v1 Announce Type: cross Abstract: Video diffusion has quickly grown into a key generative serving workload, yet producing each clip demands many denoising iterations over large spatio-temporal latents, which puts low-latency inference out of reach on a single device. A denoising step is therefore typically distributed across multiple accelerators, and TPU sub-slices have become an attractive and practical fabric for doing so. Current auto-parallel systems, however, search almost exclusively over logical device meshes and disregard how a chosen sharding is actually laid out on the physical TPU interconnect – an oversight that leaves large, topology-dependent performance on the table. We address this gap with AoiZora, a compiler-mediated topology planner built for low-latency video diffusion inference on TPU sub-slices. Its guiding principle is to reconnect logical sharding with physical placement by drawing on different points in the compilation flow: AoiZora first eliminates weak sharding candidates from inexpensive pre-compilation IRs, then compiles only the ones that survive and orders their physical placements using compiled HLO together with a topology-aware communication model. The winning plan is realized along the ordinary compiler path, leaving model code, compiler lowering, collective kernels, and network routing entirely intact. On TPU v5e sub-slices, AoiZora reduces Wan 2.1 one-step denoising latency by as much as 1.42x relative to existing solutions.

20.
arXiv (CS.CV) 2026-06-11

MLT-Dedup: Efficient Large-Scale Online Video Deduplication via Multi-Level Representations and Spatial-Temporal Matching

The explosive growth of user-generated video content on online platforms is accompanied by the emergence of numerous near-duplicate videos–videos that are identical or highly similar but differ by partial edits. These duplicates degrade user experience and increase storage and bandwidth costs, making large-scale video deduplication a critical task. Existing video deduplication frameworks face a fundamental challenge in retrieving sufficient high-quality candidates under a limited index budget, as well as trade-offs between efficiency and precision. To address these issues, we propose MLT-Dedup, an efficient large-scale online video deduplication framework with Multi-Level representations and spatial-Temporal matching. Our approach employs a Multi-Level Video Encoder (ML-VE) to extract both fine-grained frame-level and sparse clip-level embeddings: sparse embeddings support efficient candidate retrieval, while fine-grained embeddings are loaded for precise pairwise matching. During matching, we introduce DiF-SiM, a Differential Feature-enhanced Similarity Module capable of locating duplicated temporal segments and providing reliable similarity evidence to support policy-driven deduplication decisions. Extensive experiments on a real-world large-scale platform demonstrate that MLT-Dedup reduces online repetition rates by 91% at 90% precision. Furthermore, our sparse retrieval design achieves a 5x increase in indexing capacity, enabling broader candidate coverage in real-world deployment.

21.
arXiv (CS.AI) 2026-06-19

HilDA: Hierarchical Distillation with Diffusion for Advancing Self-Supervised LiDAR Pre-trainin

arXiv:2606.20189v1 Announce Type: cross Abstract: Leveraging Vision Foundation Models (VFMs) for camera-to-LiDAR knowledge distillation offers a promising solution to the scarcity of annotated data needed to represent the immense geometric and kinematic diversity of real-world autonomous driving (AD). However, current approaches typically treat VFMs as black-box teachers, relying exclusively on frame-wise feature similarity. Consequently, they do not fully exploit the teacher's layer-wise semantic structure and global context, as well as the rich spatiotemporal information inherent in LiDAR sequences. We propose HilDA, a self-supervised pretraining framework for LiDAR backbones that better captures the semantic what and geometric where needed for driving tasks. HilDA combines hierarchical distillation comprising multi-layer distillation for progressive semantic alignment and global context distillation for scene-level semantics, with a temporal occupancy diffusion objective promoting spatiotemporal consistency. Models pre-trained with HilDA achieve state-of-the-art results on cross-modal distillation benchmarks and outperform models trained via prior distillation approaches on 3D object detection, scene flow, and semantic occupancy prediction. Code available at: https://maxiuw.github.io/hilda.

23.
bioRxiv (Bioinfo) 2026-06-16

AutoZyme: An Autonomous Agentic Framework to Optimize Bioinformatics Software

Performance bottlenecks in widely used genomics and bioinformatics software present a substantial and growing burden as biological datasets continue to increase in size and number. Relieving these bottlenecks relies largely on expert manual optimization and therefore remains difficult to scale. Here we present AutoZyme, an agentic framework for scientific software optimization. Given a target function, AutoZyme builds benchmarks, identifies bottlenecks, and iteratively tests code changes, retaining only those that improve runtime while preserving output. We evaluated AutoZyme on 45 functions, improving runtime without substantial memory increases in over 95% of cases considered. Across 38 functions from Seurat, Scanpy and related packages in genomics and bioinformatics, AutoZyme reduced runtime by a median of 8.52-fold, with the largest reductions exceeding 676-fold. The optimized functions are distributed through AutoZyme-Library as drop-in replacements for existing analysis pipelines. We also release AutoZyme as a reusable framework for optimizing additional user-specified packages and functions.

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

T2MM: An LLM Supported Architecture For Inquiry-Based Modeling

Model Construction is a foundational practice in science learning that relies on visualization and interactivity. Large Language Models, increasingly augmented with multimodal capabilities, have been integrated in education contexts to support learning. However, these tools lack visual interactivity that is required by some learning contexts. We introduce Text to Multimodal Model (T2MM), a robust, dynamic LLM supported architecture that assists in model construction within the open inquiry ecology-based modeling software Virtual Experimental Research Assistant (VERA). T2MM accounts for the current context of the learner's model and creates interactive models, rather than static images, enabling the model to remain responsive to manual adjustment. To measure technical feasibility, we evaluate T2MM through a custom procedurally generated dataset of natural language learner modeling requests and target models within the VERA system. T2MM outperforms a baseline model generation architecture implemented through LLM-supported full code generation, common in the literature, across all measured success metrics. Our contribution not only outlines LLM integration into a inquiry-based learning modeling tool, but also describes a possible architecture through which more interactive multimodal LLM tools can be created.

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

Free Energy Heuristics: Fast-And-Frugal Cognition as Active Inference Under Uncertain Precision

作者:

Chain-of-thought (CoT) improves large language models' performance in math and symbolic reasoning. But on planning, contested ethics, and tasks where the model cannot check itself, more reasoning makes things worse. Both effects are documented; what has been missing is a principled account of which property decides the outcome. We argue it is meta-uncertainty: how unsure the model is about the reliability of its own evidence. When that uncertainty is high, extra reasoning stops adding signal and starts manufacturing false confidence. We prove that the policy minimizing expected free energy under uncertain precision stops integrating cues after a finite number of high-validity ones when the precision prior is heavy-tailed (Theorem 2.6.1), and under a Descending Dominance condition, is sample-wise identical to take-the-best (Theorem 2.7.4). Fast-and-frugal heuristics and active inference are, then, two descriptions of the same computation. The prediction is that on high-meta-uncertainty items, longer CoT should degrade accuracy. We score the regime per item (simulate-and-recover rho > 0.96), build FEH-79, a benchmark of Knightian frames with matched controls, and run a pre-registered study across seven models (five open-weight 3B-32B, two frontier), five CoT lengths, and 7,875 responses. The gate, fixed before any data, required a negative interaction with posterior probability above 0.95 and an accuracy drop of more than 6 points. It held. The high-regime drop is 17.3 points (95% CI [7.7, 25.5]); matched items with definite answers show no cost. The effect is regime-dependent: decisive in capable mid-to-large models, directional in the two frontier systems, absent-to-reversed in the weakest. The framework answers when CoT helps and unifies the Bayesian and fast-and-frugal traditions: less-is-more effects are evidence about the meta-uncertainty regime, not against Bayesian cognition.