cập nhật 1 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.9 giờ sau khi CVE được công bố (n = 5187, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

20
Lipschitz-Controlled Flow Matching for Robust Image Restoration
📄 Paper HF Daily Papers 10 ngày trước

Flow-matching models can produce high-quality image restorations, but their learned dynamics may amplify small input perturbations and make reconstructions unstable. We introduce LipsFlower to reduce this amplification. We derive stability bounds for Flow-from-Y, which initialize…

🅲 hạng C
20
Bits or permutations? Spending a fixed inference budget on weight precision or on option-order averaging in small local language models
📄 Paper HF Daily Papers 10 ngày trước

Local language models can save memory by storing weights in fewer bits, and they can reduce sensitivity to the order of answer options by averaging a few reorderings. We ask whether the first makes the second worse, and which is the cheaper way to spend a fixed budget. On Qwen3-0…

🅲 hạng C
20
Structured Confidence Perturbation via Fisher Geometry for Adversarial Training
📄 Paper HF Daily Papers 10 ngày trước

Adversarial training is often plagued by "pseudo-attacks", perturbations that significantly increase the loss value but fail to truly alter the model's confidence structure. To address this, we propose two complementary approaches to directly attack and defend against confidence …

🅲 hạng C
20
Dual Flow: Joint Image-Measurement Interpolation for Inverse Problems
📄 Paper HF Daily Papers 8 ngày trước

Generative model-based approaches to linear inverse problems typically use the acquired noisy measurement to condition or guide sampling in the image domain. In this work, we introduce Dual Flow, a novel joint-flow model for solving linear inverse problems by jointly estimating t…

🅲 hạng C
20
BrickFlow: Connectivity-Guided Brick Reconstruction
📄 Paper HF Daily Papers 8 ngày trước

Given a set of LEGO parts and an image of an assembled object, our task is to infer the pose of each part to assemble the object. In contrast with traditional 3D reconstruction, doing so requires satisfying discrete physical constraints, which provide structure but render the pro…

🅲 hạng C
20
GPBam: A Retrieval-Aware German Public Law Exam Benchmark
📄 Paper HF Daily Papers 7 ngày trước

Legal reasoning in civil-law systems is not rule-lookup: the German state examination asks for a structured opinion (Gutachten) that names the governing norms, applies them to the facts, and argues to a conclusion. We introduce GPBam (German Public Law Bar-style Exam), 81 public-…

🅲 hạng C
20
WeightBench: Evaluating Language Models as Weight-Space Programmers
📄 Paper HF Daily Papers 7 ngày trước

Recent work shows that large language models (LLMs) can operate directly on the parameters of other neural networks. They can read what a network was trained to do, fix a network that fails, and write working networks from scratch, all without gradient descent. This capability ha…

🅲 hạng C
20
FLORA: An Open Model Suite for Scaling Robotics Data Engines
📄 Paper HF Daily Papers 29 ngày trước

The life-cycle of robotics foundation models crucially depends on data labels. Outcome reward labels are needed for monitoring real-world deployments. Process reward labels are needed during RL post-training. Timestamped captions are needed for filtering and balancing pretraining…

🅲 hạng C
20
Sub-monolayer tracking of molecular states at buried interfaces
📄 Paper HF Daily Papers 29 ngày trước

Phenomena responsible for emerging technologies originate from novel molecular states at buried interfaces. Yet quantitatively resolving these features is out of reach in most cases. Resonant scattering has demonstrated sensitivity to these local states but is limited due to a la…

🅲 hạng C
20
AuditFL: A Contract-Backed Clearing Layer for Open Federated Learning
📄 Paper HF Daily Papers 21 ngày trước

Federated learning (FL) keeps raw data local, but most deployments still rely on a trusted coordinator for client admission, checkpoint distribution, update collection, aggregation, and rewards. This paper presents AuditFL, a contract-backed clearing layer for auditable FL in ope…

🅲 hạng C
20
Going Deeper With Memories
📄 Paper HF Daily Papers 17 ngày trước

Byte level language models avoid tokenizer dependence and provide universal coverage, but processing every byte at full resolution is expensive. We introduce DeepMem, a causal multiscale architecture that separates semantic compression from exact byte preservation. A learned inve…

🅲 hạng C
20
GigaSpeech 3: Scaling Multi-Dialect Arabic Speech Recognition with Weakly Labeled Data
📄 Paper HF Daily Papers 17 ngày trước

Dialectal Arabic speech recognition remains constrained by the scarcity of dialect-resolved transcribed speech despite the abundance of web audio. We introduce GigaSpeech 3, a corpus of 39,000 hours and 10 million weakly transcribed speech segments covering Algerian, Egyptian, Ir…

🅲 hạng C
20
Kierston & KierstonBench: Simulation of Allentown, PA and Evaluation of Language Models in Crime Investigation and Surveillance Tasks
📄 Paper HF Daily Papers 17 ngày trước

Large language models are candidates for collecting and analyzing records in criminal investigations and mass surveillance. Their capability and accuracy in this work cannot currently be measured. Real deployments lack the ground truth needed to score a model's conclusions, and n…

🅲 hạng C
20
Cross-Prompt Reuse of Entity-Replacement Responses
📄 Paper HF Daily Papers 21 ngày trước

With model weights fixed, we measure how much of an entity-replacement response transfers between English factual questions, beyond whether answers change. We add the hidden-state change from two source questions to a target question about the same entity, comparing the predicted…

🅲 hạng C
20
SphereFlow: Missing Modality Imputation via Geometric Transport on Hypersphere
📄 Paper HF Daily Papers 17 ngày trước

Missing modality imputation aims to synthesize unobserved modalities from observed ones. Existing methods treat each modality as living on its own latent manifold, forcing the generator to learn a long, unstructured jump between them. We present SphereFlow, which takes a fundamen…

🅲 hạng C
20
Horizon-Scalable Q-Learning
📄 Paper HF Daily Papers 13 ngày trước

Learning accurate off-policy state-action value functions (Q-functions) from offline datasets becomes harder as the task horizon grows. One-step temporal-difference (TD) learning bootstraps after every transition, so small per-step errors accumulate along the horizon, and early s…

🅲 hạng C
20
Knowledge Graph-based Retrieval-Augmented Generation for Schema Matching
📄 Paper HF Daily Papers 14 ngày trước

Traditional similarity-based schema matching methods fail to resolve semantic ambiguities and conflicts in complex, domain-specific mappings due to a lack of commonsense and domain-specific knowledge. In parallel, large language models (LLMs) without sufficient background knowled…

🅲 hạng C
20
Energy-Tweedie: Score meets Score, Energy meets Energy
📄 Paper HF Daily Papers 13 ngày trước

Denoising and score estimation are classically linked through Tweedie's formula, which relates the posterior mean under Gaussian noise to the Stein score of the noisy marginal. In this work, we extend this perspective beyond Gaussian noise to a broad class of Gibbs (energy-based)…

🅲 hạng C
20
Click3R: Interactive Stereo 3D Reconstruction with Sparse Correspondence Clicks
📄 Paper HF Daily Papers 11 ngày trước

Despite impressive progress, existing feed-forward large 3D reconstruction models produce a single, irrevocable prediction. When these models fail, there is no mechanism to correct their mistakes. To address this limitation, we introduce Click3R, a framework for interactive geome…

🅲 hạng C
20
Prompt2Echo (P2Echo): Text-Prompted Multi-View Echocardiography Segmentation with One Model
📄 Paper HF Daily Papers 10 ngày trước

Automated segmentation in multi-view echocardiography is essential for comprehensive cardiac assessment, yet remains challenging due to substantial anatomical and appearance variability across standard acoustic windows. In this paper, we present P2Echo, a unified framework capabl…

🅲 hạng C
20
LO-World: Unified BEV Latent Modeling for Joint 4D Occupancy and LiDAR Forecasting
📄 Paper HF Daily Papers 11 ngày trước

LiDAR point clouds and 3D semantic occupancy represent two distinct modalities capturing fine-grained metric geometry and dense volumetric semantics, respectively, holding natural potential for mutual complementarity. However, existing world models typically forecast these modali…

🅲 hạng C
20
OmniSpectra: A Unified Foundation Model for Universal Spectra Representation Learning
📄 Paper HF Daily Papers 28 ngày trước

Standard sequence models encode position by token rank rather than physical coordinate, typically forcing practitioners to destructively resample continuous physical signals such as spectra observed across heterogeneous instruments. We identify this coordinate mismatch as a struc…

🅲 hạng C
20
QFabric: Guarded Cross-Domain Task Recovery and Its Limits on a Linux-RTOS Board
📄 Paper HF Daily Papers 19 ngày trước

Heterogeneous embedded boards pair a Linux application processor with a real-time microcontroller (MCU), which suggests moving a task between the two domains when its timing degrades. We present QFabric, a prototype that treats cross-domain placement as guarded recovery from a vi…

🅲 hạng C
20
Length Is Cheap, Competition Is Not: Attention Predicts Context Rot in Retrieval
📄 Paper HF Daily Papers 17 ngày trước

Why do language models fail on long inputs? The common answer is length. We show that, for retrieval, length is cheap and competition is not. On five open models (0.5B to 3B parameters, four families), neutral filler costs nothing: accuracy stays at 0.97 to 1.00, up to 32K tokens…

🅲 hạng C
20
Alloy: A Multi-Material Physics Engine for Robot Learning
📄 Paper HF Daily Papers 8 ngày trước

Robots handle much more than rigid objects: towels, cables, water, sand. The simulators used to train robots at scale are strongest on rigid bodies, and adding another material usually means a second engine and hand-written glue between the two. We present Alloy, an open-source p…

🅲 hạng C
0
AdaPRA: Process Reward Agents with Adaptive Rubrics for Data Science
📄 Paper HF Daily Papers 28 ngày trước

Data science agents can automate end-to-end machine learning workflows, yet they remain far from competitive on human leaderboards. Agents make process errors such as insufficient exploration, unsound validation, coding bugs, and poor use of a fixed budget (re-running the same ex…

🅲 hạng C
0
A Broader Look into MLLM's Retrieval Heads
📄 Paper HF Daily Papers 28 ngày trước

Locating relevant evidence in long inputs is a core capability of Multimodal Large Language Models. Prior studies attribute this capability to retrieval heads, a sparse set of attention heads that transfer information from the context to the output. However, these analyses are co…

🅲 hạng C
0
CEPO: A General Framework for Improving Prompt Optimization in Multi-Agent Systems
📄 Paper HF Daily Papers 25 ngày trước

Multi-agent systems (MAS) require both effective coordination and specialized task execution. Existing prompt optimization approaches typically couple these functions within agent-specific prompts. We introduce Coordinator-Executor Prompt Optimization (CEPO), a general framework …

🅲 hạng C
0
TernScope: Model-Hardware Co-Design for Efficient Ternary Endoscopic Segmentation
📄 Paper HF Daily Papers 29 ngày trước

Edge medical segmentation must reconcile small model size, high accuracy, and fast inference. TernScope addresses this tradeoff through model--hardware co-design, learning a compact segmentation network whose low-bit operators also simplify hardware execution. Split-channel large…

🅲 hạng C
0
OSWAM: An Effective World Action Model with One-Step Action Generation
📄 Paper HF Daily Papers 25 ngày trước

Direct-policy World Action Models (WAM) have demonstrated the benefits of decoupling action generation from explicit future visual prediction for efficient inference in autonomous driving and embodied control. However, they still require tens of denoising steps to achieve competi…

🅲 hạng C
0
SOMA: A Benchmark for Fine-Grained Egocentric Behavior and Body-Motion Understanding
📄 Paper HF Daily Papers 25 ngày trước

Perceiving human body motion is critical for multimodal systems that understand and assist people. Yet current evaluations of Multimodal Large Language Models (MLLMs) largely focus on objects, scenes, and coarse actions, leaving their ability to reason about the body itself poorl…

🅲 hạng C