中 EN
登录 注册账户
×

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。

登录 注册账户
作者: Jun Seo ×
↻ 换一批
01.
arXiv (CS.AI) 2026-06-19

PSCT-Net: Geometry-Aware Pediatric Skull CT Reconstruction via Differentiable Back-Projection and Attention-Guided Refinement

作者:
Dong Yeong Kim↗Jaewon Choi↗Youmin Shin↗Jungyu Lee↗Myeongseop Kim↗Jinwook Choi↗Joo Whan Kim↗Young-Gon Kim↗

arXiv:2606.19867v1 Announce Type: cross Abstract: Computed Tomography (CT) is essential for diagnosing pediatric craniofacial abnormalities, yet poses radiation risks to developing anatomies. Reconstructing 3D CT from sparse bi-planar X-rays offers a low-dose alternative but is severely ill-posed. Existing methods employ geometry-agnostic feature lifting, naively projecting 2D features into 3D without explicit spatial modeling, causing depth ambiguity and degraded osseous boundaries. We present PSCT-Net, a geometry-aware framework with differentiable back-projection. Differentiable back-projection establishes a spatially faithful volumetric prior, alleviating depth ambiguity. An Attention-Guided Projection (AGP-3D) module then learns non-linear voxel-wise correspondences between 2D regions and 3D locations. A Bidirectional Mamba (BiM-3D) module captures long-range volumetric dependencies with linear complexity. We further curate a private institutional pediatric skull CT cohort, PedSkull-CT, comprising normal and pathological cases for internal evaluation, addressing the gap in adult-centric, trunk-focused datasets.

阅读与讨论 → 访问原文 →
02.
arXiv (CS.AI) 2026-06-19

Advancing DialNav through Automatic Embodied Dialog Augmentation

作者:
Leekyeung Han↗Sangwon Jung↗Hyunji Min↗Jinseong Jeong↗Minyoung Kim↗Paul Hongsuck Seo↗

arXiv:2606.19948v1 Announce Type: new Abstract: For embodied agents capable of physical interaction, the capability to create and understand dialog is crucial to ensure both safety and effectiveness. While DialNav[han2025dialnav] provides a framework for holistic evaluation of the dialog–execution loop in photorealistic indoor navigation, its performance remains limited by a critical scarcity of training data (2K episodes). To address this, we propose an automatic generation pipeline, and construct the RAINbow dataset, a large-scale training dataset with 238K episodes for DialNav. Our pipeline converts existing VLN datasets into multi-turn dialog and creates cost-efficient and high-quality dataset. Then, we introduce two additional complementary advances to unlock the data's full potential: (1) Dual-Strategy Training, a navigation training scheme to align the navigation training with the dynamic dialog-navigation loop, and (2) a localization model that leverages VLN knowledge. By combining these complementary solutions, our model substantially outperforms the baseline in success rate on both Val Seen (58.24, +89\%) and Val Unseen (29.05, +100\%) splits, establishing a new state of the art.

阅读与讨论 → 访问原文 →
03.
arXiv (CS.CL) 2026-06-19

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

作者:
ChangSu Choi↗Hoyun Song↗Dongyeon Kim↗WooHyeon Jung↗Minkyung Cho↗Sunjin Park↗NohHyeob Bae↗Seona Yu↗KyungTae Lim↗

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.

阅读与讨论 → 访问原文 →
04.
arXiv (CS.CL) 2026-06-19

Quantifying Aleatoric Uncertainty of In-Context Learning for Robust Measure of LLM Prediction Confidence

作者:
Jinseok Chung↗Minkyoung Song↗Hyunji Jung↗Namhoon Lee↗

In-Context Learning (ICL) allows LLMs to adapt to new tasks from a few demonstrations, but its reliability remains a concern: predictions are highly sensitive to both prompt design and the model's ability to understand the context, obscuring whether failures arise from data properties or model limitations. Uncertainty decomposition-separating aleatoric from epistemic sources-is particularly crucial in this setting, yet existing methods, designed for standard generation tasks, fail to capture the unique dynamics of ICL. To address this, we introduce a concept of self-function vectors, built upon Bayesian views and the mechanistic interpretability of ICL. These vectors leverage internal model representations to model the latent concept learned during in-context prompting, thereby enabling a direct estimation of aleatoric uncertainty within a Bayesian framework and circumventing the reliance on brittle input or decoding manipulations. Given the lack of established benchmarks and suitable evaluation protocols, we also propose the first and rigorous evaluation protocol, in which data is manipulated in controlled ways so as to quantify aleatoric uncertainty precisely and separately from epistemic uncertainty. With this new evaluation framework, initially grounded in synthetic tasks for conceptual development and subsequently extended to real-world datasets, we show that our proposed methodology can measure uncertainty of LLM predictions made under ICL more reliably than existing alternative methods. Moreover, we show it can be used as a practical tool for trustworthy-related applications, such as hallucination detection. Our findings pave a new direction for connecting the quantitative view of uncertainty with the mechanistic understanding of model behavior.

阅读与讨论 → 访问原文 →
05.
arXiv (CS.LG) 2026-06-18

EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts

作者:
Minseo Kim↗Minjae Lee↗Seunghyuk Oh↗Kevin Galim↗Donghoon Kim↗Coleman Hooper↗Harman Singh↗Amir Gholami↗Hyung Il Koo↗Wonjun Kang↗

arXiv:2606.18967v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a representative post-training paradigm for LLMs, enabling strong reasoning and agentic capabilities. However, rollout generation remains a dominant latency bottleneck because autoregressive sampling decodes responses sequentially and a small number of long-tailed generations often determine completion time. Speculative decoding (SD) offers a natural way to address this bottleneck, as it is a well-established technique for serving fixed LLMs that reduces latency by rapidly drafting tokens and accepting them through parallel verification while preserving the target-model distribution. However, its practical speedups do not directly carry over to RL rollouts: (i) the evolving target policy makes any fixed drafter increasingly mismatched with the policy's output distribution; and (ii) active batch sizes shrink throughout rollout decoding, shifting decoding from compute-bound to memory-bound regimes where parallel verification can exploit underutilized compute. Therefore, accelerating RL rollouts requires both a drafter that remains effective under long, high-temperature generations from an evolving policy and system-aware use of SD that avoids compute-bound regimes. We present EfficientRollout, a system-aware self-SD framework designed to address this gap for RL rollouts. EfficientRollout induces a quantized drafter from the target model (i.e. self-speculative decoding), keeping it coupled to the evolving policy without separate drafter pretraining or online adaptation. It further coordinates a system-aware SD toggle policy with acceptance-aware draft-length adaptation, enabling speculation only in beneficial regimes while matching the drafting budget to evolving drafter quality. EfficientRollout reduces rollout and end-to-end latency by up to 19.6% and 12.7%, respectively, over an accelerated AR rollout baseline, while preserving final model quality.

阅读与讨论 → 访问原文 →
06.
arXiv (CS.AI) 2026-06-18

Clin-JEPA: A Multi-Phase Co-Training Framework for Joint-Embedding Predictive Pretraining on EHR Patient Trajectories

作者:
Yixuan Yang↗Mehak Arora↗Ryan Zhang↗Baraa Abed↗Junseob Kim↗Tilendra Choudhary↗Md Hassanuzzaman↗Kevin Zhu↗Ayman Ali↗Chengkun Yang↗Alasdair Edward Gent↗Victor Moas↗…

arXiv:2605.10840v3 Announce Type: replace-cross Abstract: We present Clin-JEPA, a multi-phase co-training framework for joint-embedding predictive (JEPA) pretraining on EHR patient trajectories. JEPA architectures have enabled latent-space planning in robotics and high-quality representation learning in vision, but extending the paradigm to EHR data – to obtain a single backbone that simultaneously forecasts patient trajectories and serves diverse downstream risk-prediction tasks without per-task fine-tuning – remains an open challenge. Existing JEPA frameworks either discard the predictor after pretraining (I-JEPA, V-JEPA) or train it on a frozen pretrained encoder (V-JEPA 2-AC), leaving the encoder unaware of the rollout signal that the retained predictor must use at inference; co-training the encoder and predictor under a shared JEPA prediction objective would supply this grounding, but naïve co-training is unstable, with representation collapse and online/target drift causing autoregressive rollout to diverge. Clin-JEPA's five-phase pretraining curriculum – predictor warmup, joint refinement, EMA target alignment, hard sync, and predictor finalization – addresses each failure mode by phase, stably co-training a Qwen3-8B-based encoder and a 92M-parameter latent trajectory predictor. On MIMIC-IV ICU data, three independent evaluations support the framework: (1) latent $\ell_1$ rollout drift uniquely converges ($-$15.7%) over 48-hour horizons while baselines and ablations diverge (+3% to +4951%); (2) the encoder learns a clinically discriminative latent geometry (deteriorating-patient cohorts displace 4.83$\times$ further than stable patients in latent space, vs $\leq$2.62$\times$ for baseline encoders); (3) a single backbone outperforms strong tabular and sequence baselines on multi-task downstream evaluation. Clin-JEPA achieves mean AUROC 0.851 on ICareFM EEP and 0.883 on 8 binary risk tasks (+0.038 and +0.041 vs baseline average).

阅读与讨论 → 访问原文 →
07.
arXiv (CS.AI) 2026-06-18

Improving Scientific Document Retrieval with Academic Concept Index

作者:
Jeyun Lee↗Junhyoung Lee↗Wonbin Kweon↗Bowen Jin↗Yu Zhang↗Susik Yoon↗Dongha Lee↗Hwanjo Yu↗Jiawei Han↗Seongku Kang↗

arXiv:2601.00567v2 Announce Type: replace-cross Abstract: Adapting general-domain retrievers to scientific domains is challenging due to the scarcity of large-scale domain-specific relevance annotations and the substantial mismatch in vocabulary and information needs. Recent approaches address these issues through two independent directions that leverage large language models (LLMs): (1) generating synthetic queries for fine-tuning, and (2) generating auxiliary contexts to support relevance matching. However, both directions overlook the diverse academic concepts embedded within scientific documents, often producing redundant or conceptually narrow queries and contexts. To address this limitation, we introduce an academic concept index, which extracts key concepts from papers and organizes them guided by an academic taxonomy. This structured index serves as a foundation for improving both directions. First, we enhance the synthetic query generation with concept coverage-based generation (CCQGen), which adaptively conditions LLMs on uncovered concepts to generate complementary queries with broader concept coverage. Second, we strengthen the context augmentation with concept-focused auxiliary contexts (CCExpand), which leverages a set of document snippets that serve as concise responses to the concept-aware CCQGen queries. Extensive experiments show that incorporating the academic concept index into both query generation and context augmentation leads to higher-quality queries, better conceptual alignment, and improved retrieval performance.

阅读与讨论 → 访问原文 →
08.
arXiv (CS.AI) 2026-06-18

PosterForest: Hierarchical Multi-Agent Collaboration for Scientific Poster Generation

作者:
Jiho Choi↗Seojeong Park↗Seongjong Song↗Hyunjung Shim↗

arXiv:2508.21720v3 Announce Type: replace Abstract: Automating scientific poster generation requires hierarchical document understanding and coherent content-layout planning. Existing methods often rely on flat summarization or optimize content and layout separately. As a result, they often suffer from information loss, weak logical flow, and poor visual balance. We present PosterForest, a training-free framework for scientific poster generation. Our method introduces the Poster Tree, a structured intermediate representation that captures document hierarchy and visual-textual semantics across multiple levels. Building on this representation, content and layout agents perform hierarchical reasoning and recursive refinement, progressively optimizing the poster from global organization to local composition. This joint optimization improves semantic coherence, logical flow, and visual harmony. Experiments show that PosterForest outperforms prior methods in both automatic and human evaluations, without additional training or domain-specific supervision.

阅读与讨论 → 访问原文 →
09.
arXiv (CS.AI) 2026-06-18

Dynamic In-Group Persona Generation for Enhancing Human-AI Rapport

作者:
Yoonseok Oh↗Inseo Jung↗Jinkyu Kim↗Jungbeom Lee↗Minwoo Kang↗Suhong Moon↗

arXiv:2606.18256v1 Announce Type: cross Abstract: LLM-based chatbots are increasingly applied in interpersonal domains such as counseling and peer support, where establishing human-AI rapport is crucial yet remains challenging. In this work, we introduce a novel approach for conditioning LLMs with in-group personas, which (i) first identifies a user's primary concern and brief personal context (e.g., a computer science undergraduate worried about future career prospects), and (ii) generates a synthetic in-group persona that shares a similar primary concern while differing in background and narrative details, such as age or profession (e.g., a junior researcher at an AI startup). Furthermore, we conduct a human-subject study to systematically evaluate the effectiveness of in-group persona agents in enhancing human-AI rapport. We compare our approach against two baseline conditions: a conventional agent without persona conditioning and an agent exhibiting minimal self-disclosure (e.g., "I've felt that too"). Results from post-task questionnaires assessing rapport and user experience indicate that the in-group persona agent significantly improves perceived rapport and personal relevance compared to the baselines, and also yields more positive user experience-most notably higher engagement.

阅读与讨论 → 访问原文 →
10.
arXiv (CS.CV) 2026-06-18

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

作者:
Woojung Han↗Seil Kang↗Youngjun Jun↗Min-Hung Chen↗Fu-En Yang↗Seong Jae Hwang↗

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

阅读与讨论 → 访问原文 →
11.
arXiv (CS.CV) 2026-06-18

Cosmos 3: Omnimodal World Models for Physical AI

作者:
NVIDIA↗Aditi↗Niket Agarwal↗Arslan Ali↗Jon Allen↗Martin Antolini↗Adeline Aubame↗Alisson Azzolini↗Junjie Bai↗Maciej Bala↗Yogesh Balaji↗Josh Bapst↗…

We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-transformers architecture. By supporting highly flexible input-output configurations, Cosmos 3 seamlessly unifies critical modalities for Physical AI – effectively subsuming vision-language models, video generators, world simulators, and world-action models into a single framework. Our evaluation demonstrates that Cosmos 3 establishes a new state-of-the-art across a diverse suite of understanding and generation tasks, demonstrating omnimodal world models as scalable, general-purpose backbones for embodied agents. Our post-trained Cosmos 3 models were ranked as the best open-source Text-to-Image and Image-to-Video models by Artificial Analysis, and the best policy model by RoboArena at the time the technical report was written. To accelerate open research and deployment in Physical AI, we make our code, model checkpoints, curated synthetic datasets, and evaluation benchmark available under the Linux Foundation's OpenMDW-1.1 License at https://github.com/nvidia/cosmos and https://huggingface.co/collections/nvidia/cosmos3. The project website is available at https://research.nvidia.com/labs/cosmos-lab/cosmos3.

阅读与讨论 → 访问原文 →
12.
arXiv (CS.CV) 2026-06-18

Hand-4DGS: Feed-Forward 3D Gaussian Splatting for 4D Hand Reconstruction from Egocentric Videos

作者:
Jeongmin Bae↗Seoha Kim↗Marc Pollefeys↗Mahdi Rad↗Youngjung Uh↗Taein Kwon↗

Dynamic 3D hand reconstruction from egocentric videos is essential for next-generation computing platforms such as AR/VR and AI glasses. Despite its importance, most prior works focus either on multi-view 3D hand reconstruction or on 4D human body reconstruction. Egocentric 4D hand reconstruction remains challenging due to fast head motion, rapid hand dynamics, severe occlusions, and inherent ambiguity from single-view observations. To address these challenges, we introduce Hand-4DGS, the first feed-forward framework for reconstructing dynamic 4D hands directly from egocentric videos, enabling both fast (~60 FPS) inference and strong generalization. Our approach incorporates a mesh-guided representation for structural priors and temporal convolutions to model dynamic motion. We evaluate our framework on two challenging egocentric datasets, H2O and ARCTIC, and demonstrate significant improvements over baselines. Our method benefits from the generalization capability of feed-forward networks and effective 2D image supervision through Gaussian splatting, without requiring expensive 3D hand pose ground-truth annotations.

阅读与讨论 → 访问原文 →
13.
arXiv (CS.CV) 2026-06-18

BindEdit: Taming Attention Leakage for Precise Multi-Object Image Editing

作者:
Chaewon Park↗Soyoon Lee↗Naeun Lee↗Minjung Shin↗Seogkyu Jeon↗Kibeom Hong↗

Real image editing enables precise manipulation of visual content, yet existing methods often fail in complex multi-object scenarios, causing semantic blending, object duplication, or incomplete edits. We attribute these failures to attention leakage, where signals across spatial regions and text tokens become entangled during the denoising process. Specifically, we identify two distinct forms of leakage: Edit-Token Leakage, where ambiguous token-region alignment leads to object blending, and Source Dominance Leakage, where tokens of unchanged source objects overwhelm the attention intended for target entities. To resolve these leakages, we propose BindEdit, which enforces attention-level constraints within a single diffusion trajectory. To suppress Edit-Token Leakage, BindEdit jointly regularizes cross- and self-attention so that each target token group is bound to its corresponding spatial region while maintaining instance-level separation. To suppress Source Dominance Leakage, a cross-attention re-balancing mechanism amplifies target token influence and attenuates residual source semantics within editable regions. Moreover, a region fidelity term ensures that each target concept is expressed coherently across the entire editing mask. Additionally, we propose a comprehensive multi-object benchmark encompassing diverse object counts and categories. Extensive experiments demonstrate that BindEdit consistently outperforms existing methods within a single diffusion trajectory, maintaining robust performance across both single- and multi-object editing scenarios.

阅读与讨论 → 访问原文 →
14.
arXiv (CS.AI) 2026-06-17

Rethinking Multimodal Fusion for Time Series: Text Modalities Need Constrained Fusion

作者:
Seunghan Lee↗Jun Seo↗Jaehoon Lee↗Sungdong Yoo↗Minjae Kim↗Tae Yoon Lim↗Dongwan Kang↗Hwanil Choi↗SoonYoung Lee↗Wonbin Ahn↗

arXiv:2603.22372v2 Announce Type: replace-cross Abstract: Recent advances in multimodal learning have motivated the integration of auxiliary modalities such as text or vision into time series (TS) forecasting. However, most existing methods provide limited gains, often improving performance only in specific datasets or relying on architecture-specific designs that limit generalization. In this paper, we show that multimodal models with naive fusion strategies (e.g., simple addition or concatenation) often underperform unimodal TS models, which we attribute to the uncontrolled integration of auxiliary modalities which may introduce irrelevant information. Motivated by this observation, we explore various constrained fusion methods designed to control such integration and find that they consistently outperform naive fusion methods. Furthermore, we propose Controlled Fusion Adapter (CFA), a simple plug-in method that enables controlled cross-modal interactions without modifying the TS backbone, integrating only relevant textual information aligned with TS dynamics. CFA employs low rank adapters to filter irrelevant textual information before fusing it into temporal representations. We conduct over 20K experiments across various datasets and TS/text models, demonstrating the effectiveness of the constrained fusion methods. Code is available at: https://github.com/seunghan96/cfa.

阅读与讨论 → 访问原文 →
15.
arXiv (CS.CL) 2026-06-17

When Multiple Scripts Matter: Evaluating ASR in Clinical Settings

作者:
Jean Seo↗Minkyu Kim↗Jeonguk Lee↗Jisoo Jung↗Wooseok Han↗Eunho Yang↗

Automatic speech recognition (ASR) in non-English clinical settings is challenged by multiscript variability, where the same term may appear in multiple valid orthographic forms. Conventional string-matching evaluation metrics often underestimate ASR performance by treating orthographic variants as errors. To address this issue, we introduce MultiClin, a clinical ASR benchmark designed to evaluate robustness to multiscript variability. Experiments across diverse ASR models show that multiscript-aware evaluation provides a fairer assessment of recognition quality than conventional single-reference evaluation. We further investigate the impact of script consistency during training and find that inconsistent script mappings increase orthographic uncertainty and hinder model convergence, with a balanced 50% mapping ratio producing the highest entropy. In contrast, script unification consistently yields the best ASR performance. Our dataset and code are publicly available at: https://github.com/aitrics-ronaldo/Interspeech_MultiClin.

阅读与讨论 → 访问原文 →
16.
arXiv (CS.LG) 2026-06-16

Airport Terminal Passenger Queue Forecasting for Departure Gates and Security Checkpoints

作者:
Juhwan Lee↗Seokbin Yoon↗Keumjin Lee↗Hojong Baik↗Seyeon Jung↗

arXiv:2606.07622v2 Announce Type: replace Abstract: Accurate passenger queue forecasting in airport terminals is essential for efficient departure operations, as it enables proactive congestion management. However, time-varying passenger demand and heterogeneous facility usage across multiple departure facilities make forecasting challenging. In this work, we propose a passenger queue forecasting framework that learns historical passenger flow patterns from operational data. The proposed model employs a Transformer-based architecture to capture temporal dependencies and inter-facility correlations using past queue length and waiting time at departure gates and security checkpoints, together with passenger throughput at check-in islands. The learned representations are mapped to two facility-specific prediction heads to predict queue length and waiting time at departure gates and security checkpoints. Experimental results demonstrate accurate forecasts up to two hours ahead. The proposed approach offers practical real-time decision support for proactive queue management and staff reallocation in airport terminal operations.

阅读与讨论 → 访问原文 →
17.
arXiv (CS.LG) 2026-06-16

Tangram: Unlocking Non-Uniform KV Cache Compression for Efficient Multi-turn LLM Serving

作者:
Hyungmin Kim↗Minsoo Kim↗Hongseok Kim↗Jungwook Choi↗

arXiv:2606.06302v2 Announce Type: replace Abstract: Multi-turn LLM serving accumulates dialogue history whose Key-Value (KV) cache grows with every turn and every user, quickly exceeding the model weights themselves and making memory – not compute – the binding constraint on throughput. Non-uniform KV compression, which allocates heterogeneous budgets across attention heads, preserves accuracy far better than uniform schemes, yet remains impractical: modern serving stacks assume identical KV lengths across heads, so heterogeneity traps freed memory as page fragmentation, spends up to 25% of prefill time reclaiming scattered pages, and skews GPU workloads that inflate decode latency by up to $1.7\times$ or burn 15–20% of each decode step on re-planning. We observe that this heterogeneity need not be discovered at runtime: head-wise retention follows a two-level structural regularity – an input-invariant head ranking with narrowly bounded per-head ratios – that can be calibrated offline from as few as 50 samples. Building on this insight, we present Tangram, a serving framework that statically resolves what prior systems handle dynamically: Budget Reservation fixes each head's post-compression footprint at scheduling time, eliminating page reclamation; Ragged Paging clusters similar-budget heads into independent page tables, turning fragmentation into reclaimable memory; and Ahead-of-Time Load Balancing precomputes balanced GPU partitions with zero runtime planning. Implemented on vLLM, Tangram serves as a drop-in substrate for existing non-uniform compression methods, matching their accuracy while improving end-to-end throughput by up to $2.6\times$ over the full-KV baseline. Our implementation is publicly available at https://github.com/aiha-lab/TANGRAM.

阅读与讨论 → 访问原文 →
18.
arXiv (CS.LG) 2026-06-16

Not All Retrievals are Useful: Cross-Attention for Input-Aware RAG in Time Series Forecasting

作者:
Seunghan Lee↗Jaehoon Lee↗Jun Seo↗Sungdong Yoo↗Minjae Kim↗Tae Yoon Lim↗Dongwan Kang↗Hwanil Choi↗SoonYoung Lee↗Wonbin Ahn↗

arXiv:2603.14709v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) enhances zero-shot time series (TS) forecasting by leveraging external knowledge bases, yet existing approaches overlook input-level relevance when fusing retrieved samples with the query. We argue that not all retrievals are equally useful, and irrelevant ones can degrade performance. To this end, we propose Cross-RAG, a zero-shot RAG-based forecasting framework that selectively attends to query-relevant retrieved samples via query–retrieval cross-attention. By modeling input-level relevance between the query and retrieved samples, Cross-RAG jointly incorporates three sources of information: 1) the query itself, 2) the retrieved samples, and 3) their relational interactions. In particular, this input-aware design enables Cross-RAG to remain stable as the number of retrieved samples $k$ grows, whereas prior methods without cross-attention require careful $k$ tuning to avoid degradation from irrelevant retrievals. Extensive experiments demonstrate that Cross-RAG consistently improves zero-shot forecasting performance across multiple TSFM backbones and various RAG methods, with additional analyses confirming its effectiveness across various retrieval scenarios. Code is available at https://github.com/seunghan96/cross-rag/.

阅读与讨论 → 访问原文 →
19.
arXiv (CS.LG) 2026-06-16

ReQAT: Achieving Full-Precision Reasoning Accuracy with 4-bit Floating-Point Quantization-Aware Training

作者:
Janghwan Lee↗Sihwa Lee↗Jinseok Kim↗Yongjik Kim↗Jieun Lim↗Jinwook Oh↗Jungwook Choi↗

arXiv:2606.15682v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) achieve strong problem-solving through long chain-of-thought, but their deployment is constrained by the high cost of full-precision inference and growing KV cache footprints. Microscaled FP4 formats enable efficient FP4 deployment; however, fully quantizing weights, activations, and KV caches (W4A4KV4) causes severe reasoning degradation that existing PTQ and QAT fail to recover. We identify that FP4 failures concentrate on low-entropy tokens–precise symbolic commitments such as digits and operators–where quantization noise inflates sampling errors that cascade through reasoning traces. Based on this insight, we propose ReQAT, a reasoning-centric FP4 training framework with three components: (i) Trace-Aligned QAT (TAQ), which revisits identical reasoning traces to focus updates on critical low-entropy decisions; (ii) Selective Entropy Minimization (SEM), which reinforces confidence at low-entropy positions; and (iii) Q-FIT, a quantization-friendly initialization that jointly calibrates RoPE-consistent KV cache transformations to stabilize QAT. Under the same training budget, ReQAT not only recovers but surpasses BF16 fine-tuning accuracy, while delivering up to 3.9x throughput speedup on NVIDIA DGX Spark and 3.1x on B200.

阅读与讨论 → 访问原文 →
20.
arXiv (CS.LG) 2026-06-16

Probabilistic Signature Inversion: Learning Conditional Distributions from Truncated Signatures

作者:
Junoh Kang↗Kiseop Lee↗Bohyung Han↗

arXiv:2606.15332v1 Announce Type: new Abstract: The signature transform is a principled feature map for continuous-time paths, valued for its uniqueness and universality. Recovering a path from its truncated signature is, however, structurally ill-posed because the truncated signature map is not injective. We therefore reframe truncated signature inversion as a probabilistic problem – learning the conditional distribution of a path given its truncated signature – and adopt a signature-conditioned flow matching model as a practical estimator. This probabilistic formulation elucidates the fundamental difficulty of inversion: Bayes reconstruction error quantifies the irreducible uncertainty remaining after conditioning on a statistic. We derive the Bayes-optimal error under linear statistics, obtaining a closed form for log-GBM and numerically tractable formulas for log-fBM and OU, yielding a concrete theoretical baseline for model validation. This baseline upper-bounds the Bayes error under truncated-signature conditioning, since truncated signatures provide richer information than linear statistics. Experiments show that empirical reconstruction errors under linear-statistics conditioning faithfully align with the theory-derived baseline, while errors decrease when the statistic is replaced with truncated signatures. Moreover, generated paths faithfully recover the conditioning signature while preserving key distributional and temporal structures, indicating that the estimator is well-calibrated to the target conditional distribution. Together, these results establish a well-posed probabilistic framework for truncated-signature inversion, with applicability demonstrated on real financial data beyond the parametric process families covered by theory.

阅读与讨论 → 访问原文 →
21.
arXiv (CS.AI) 2026-06-16

From Detection to Recovery: Operational Analysis on LLM Pre-training with 504 GPUs

作者:
Daemyung Kang↗Eunjin Hwang↗Hanjeong Lee↗HyeokJin Kim↗Hyunhoi Koo↗Jeongkyu Shin↗Jeongseok Kang↗Jihyun Kang↗Jinho Heo↗Joongi Kim↗Junbum Lee↗Jungseung Yang↗…

arXiv:2605.09370v5 Announce Type: replace-cross Abstract: Large-scale AI training is fundamentally a distributed systems problem, where hardware failures are routine operating conditions rather than rare exceptions, yet public operational evidence from production training clusters remains limited. This report presents an empirical analysis of a 63-node NVIDIA B200 production cluster (504 GPUs), using 55 days of Prometheus time-series data and 73 days of operational logs covering 224 multi-node training sessions. The environment is cross-organizational: five parties (SKT, Upstage, Lablup, NVIDIA Korea, VAST Data) share a unified monitoring pipeline. This enabled joint diagnosis of a 60-node-scale storage I/O bottleneck absent in 2-4-node tests, a production-scale phenomenon no single team could isolate alone. We perform three quantitative analyses yielding four findings. First, over 751 Prometheus metrics and 10 XID-identified GPU failures, no single metric is consistently dominant across failure types, motivating multi-signal detection. Second, 523 checkpoint events trace the save/load path from GPU VRAM to the NFS server: restart loading reaches 21.5% of maximum read bandwidth (700 GB/s) and save bursts 16.0% of maximum write bandwidth (250 GB/s), with NFS/RPC queueing and transport-layer backlog rising together. Third, across 224 sessions over 73 days, node exclusions concentrate so the top 3 of 63 nodes account for over 50%. Fourth, auto-retry chain analysis shows a 33.3% success rate over 12 chains (73 attempts), 2.7x the 12.5% manual rate, with a median retry interval of 11 minutes (IQR 10-11). All analyses are grounded in production infrastructure providing session-level workload management, GPU-centric scheduling, and unified observability.

阅读与讨论 → 访问原文 →
22.
arXiv (CS.CL) 2026-06-16

RoTRAG: Rule of Thumb Reasoning for Conversation Harm Detection with Retrieval-Augmented Generation

作者:
Juhyeon Lee↗Wonduk Seo↗Junseo Koh↗Seunghyun Lee↗Haihua Chen↗Yi Bu↗

Detecting harmful content in multi turn dialogue requires reasoning over the full conversational context rather than isolated utterances. However, most existing methods rely mainly on models internal parametric knowledge, without explicit grounding in external normative principles. This often leads to inconsistent judgments in socially nuanced contexts, limited interpretability, and redundant reasoning across turns. To address this, we propose RoTRAG, a retrieval augmented framework that incorporates concise human written moral norms, called Rules of Thumb (RoTs), into LLM based harm assessment. For each turn, RoTRAG retrieves relevant RoTs from an external corpus and uses them as explicit normative evidence for turn level reasoning and final severity classification. To improve efficiency, we further introduce a lightweight binary routing classifier that decides whether a new turn requires retrieval grounded reasoning or can reuse existing context. Experiments on ProsocialDialog and Safety Reasoning Multi Turn Dialogue show that RoTRAG consistently improves both harm classification and severity estimation over competitive baselines, with an average relative gain of around 40% in F1 across benchmark datasets and an average relative reduction of 8.4% in distributional error, while reducing redundant computation without sacrificing performance.

阅读与讨论 → 访问原文 →
23.
arXiv (CS.CL) 2026-06-16

The Truth Stays in the Family: Enhancing Contextual Grounding via Inherited Truthful Heads in Model Lineages

作者:
Miso Choi↗Seonga Choi↗Mincheol Kwon↗Woosung Joung↗Jinkyu Kim↗Jungbeom Lee↗

Recent advances in large language models (LLMs) have produced many specialized multimodal LLMs (MLLMs) that share common foundational LLMs, forming distinct model lineages. It remains unclear whether a fundamental behavioral link exists between the foundational LLMs and downstream variants. We investigate this question by quantifying head-level context-truthfulness scores. Across diverse LLM and MLLM lineages, including Vicuna-, Qwen2.5-, LLaMA2-, and Mistral-based models, we find that Truth Scores are strongly preserved within model families, even after instruction tuning or multimodal adaptation. We further show that this inheritance is consistent with attention-head weight preservation, and that context-truthful heads attend to query-relevant evidence. Building on this finding, we propose TruthProbe, a soft-gating strategy that amplifies context-truthful heads while preserving other head contributions. TruthProbe improves contextual truthfulness on HaluEval and reduces multimodal hallucination on POPE and CHAIR, with base-LLM Truth Scores transferring effectively to their fine-tuned LLM and MLLM descendants. Code is available at https://github.com/miso-choi/TruthProbe.

阅读与讨论 → 访问原文 →
24.
arXiv (CS.CL) 2026-06-16

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

作者:
NVIDIA↗Aaron Blakeman↗Aaron Thomas↗Aastha Jhunjhunwala↗Abhibha Gupta↗Abhinav Khattar↗Adam Rajfer↗Adi Renduchintala↗Adil Asif↗Aditya Vavre↗Adriana Flores Miranda↗Ahmad Bilal↗…

We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 trillion text tokens, then extended the context length to 1M tokens, and post-trained using Supervised Fine Tuning (SFT), Reinforcement Learning (RL), and Multi-teacher On-Policy Distillation (MOPD). Nemotron 3 Ultra is our most capable model yet, employing multiple key technologies - LatentMoE, Multi Token Prediction (MTP), NVFP4 pre-training, multi-environment RLVR, MOPD, and reasoning budget control. Nemotron 3 Ultra achieves up to ~6x higher inference throughput as compared to state-of-the-art publicly available LLMs while attaining on-par accuracy. The state-of-the-art accuracy, high inference throughput, and 1M token context length make Nemotron 3 Ultra ideal for long-running autonomous agentic tasks. We open-source the base, post-trained, and quantized checkpoints, along with the training data and recipe on HuggingFace.

阅读与讨论 → 访问原文 →
25.
arXiv (CS.CV) 2026-06-16

Geometric Action Model for Robot Policy Learning

作者:
Jisang Han↗Seonghu Jeon↗Jaewoo Jung↗Ren\'e Zurbr\"ugg↗Honggyu An↗Tifanny Portela↗Marco Hutter↗Marc Pollefeys↗Seungryong Kim↗Sunghwan Hong↗

Generalist robot policies must follow user instructions while reasoning about how objects, cameras, and robot actions interact in the 3D physical world. Recent vision-language-action models (VLAs) and video world-action models (WAMs) inherit strong semantic or temporal priors from large-scale foundation models, but they still operate primarily on 2D image frames or 2D-derived latent spaces, leaving implicit the 3D geometry required for contact-rich manipulation. We propose the Geometric Action Model (GAM), a language-conditioned manipulation policy that directly repurposes a pretrained geometric foundation model (GFM) as a shared substrate for perception, temporal prediction, and action decoding. GAM splits the GFM at an intermediate layer: the shallow layers serve as an observation encoder, and a causal future predictor inserted at the split layer forecasts future latent tokens conditioned on language, proprioception, and action history. The predicted future tokens are then routed through the remaining GFM blocks for feature propagation and decoding, allowing a single backbone to produce both future geometry and actions. This design equips the GFM with language-conditioned temporal world modeling through minimal architectural modification while preserving its rich geometric priors. Across a broad suite of simulation and real-robot manipulation benchmarks, GAM is more accurate, more robust, faster, and lighter than current foundation-model-scale baselines.

阅读与讨论 → 访问原文 →