cập nhật 46 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5263, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

20
GameVerse: A Minute-Scale Gameplay Dataset for Long-Horizon Interactive World Modeling
📄 Paper HF Daily Papers 20 ngày trước

Recent advances in interactive world models have made it possible to generate controllable, dynamic environments from action inputs. Yet current models struggle to maintain coherence beyond roughly one minute of rollout, a limitation rooted not in model capacity but in the scarci…

🅲 hạng C
20
dNaViT: Discrete Codes are General-Purpose Visual Representations
📄 Paper HF Daily Papers 11 ngày trước

Discrete autoregressive modeling, notably through next-token prediction, has become a cornerstone of modern language models. Extending this paradigm to vision allows visual and language models to converge on a unified framework, thereby fostering shared methodology and infrastruc…

🅲 hạng C
20
Duo: A Reciprocal World Model for Full-Duplex Interaction
📄 Paper HF Daily Papers 9 ngày trước

In this report, we introduce the Reciprocal World Model (RWM) and present Duo v1, a full-duplex world model that continuously perceives audiovisual inputs while responding to users in real time. The RWM treats intelligence and physical reality as equally fundamental to what const…

🅲 hạng C
20
MMFlash: Faster Speculative Decoding for Vision-Language Models
📄 Paper HF Daily Papers 7 ngày trước

Speculative decoding accelerates generation by letting a lightweight drafter propose tokens for parallel verification by a target model. Diffusion drafters such as DFlash propose an entire token block in a single forward pass, but mainly focus on text-only tasks, leaving multimod…

🅲 hạng C
20
Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL
📄 Paper HF Daily Papers 27 ngày trước

Rubric-based rewards enable effective reinforcement learning on non-verifiable tasks. However, because these rewards are typically defined as a weighted measure of rubric coverage, models are trained primarily to maximize a recall objective. As a result, RL-trained models produce…

🅲 hạng C
20
LociArt: A Unified Paradigm for Free-Style Local Video Stylization
📄 Paper HF Daily Papers 24 ngày trước

Video stylization typically transforms entire scenes, while local artistic editing requires precise region--style association, spatial control, and temporal consistency. We introduce LociArt, a unified paradigm for free-style local video stylization that explicitly specifies wher…

🅲 hạng C
20
EmbeddingGemma 2: Unified and Efficient Multimodal Representations
📄 Paper HF Daily Papers 24 ngày trước

We present EmbeddingGemma 2, an open multimodal embedding model which natively represents text, images, audio, video, and combinations thereof in a unified space. Our approach introduces improvements such as simplified per-layer embeddings and a multi-stage curriculum with modali…

🅲 hạng C
20
HairDeck: Animation-Ready Stylized Hair Cards from a Single Image
📄 Paper HF Daily Papers 22 ngày trước

The hair of stylized characters in games and avatars is built from hair cards: artist-placed ribbons whose geometry is the visible hair, animated by spring bones. Existing image-based methods produce realistic hair or a single fused mesh, while CHARM, the only generator of styliz…

🅲 hạng C
20
WeFair: Fidelity-Aware Alignment from Human Feedback for Personalized Query Rewriting in Short-Video Search
📄 Paper HF Daily Papers 21 ngày trước

Short-video search needs compact query rewriters that recover users' personalized intent from ambiguous queries under strict latency constraints. Existing LLM-based methods have improved rewriting by using synthetic reasoning and subsequent consumption-behavioral feedback. Howeve…

🅲 hạng C
20
Latent Reasoning in Continuous Space for Unified Multimodal Models
📄 Paper HF Daily Papers 21 ngày trước

Unified Multimodal Models (UMMs) achieve remarkable success on diverse multimodal understanding and generation tasks, yet they still struggle to effectively leverage language-based chain-of-thought reasoning for image generation. As a result, existing reasoning-augmented UMMs oft…

🅲 hạng C
20
NorthCUA Technical Report: Turbocharging Computer-Use Agents through Experience at Scale
📄 Paper HF Daily Papers 19 ngày trước

Scaling computer-use agents from individual actions to complex software work requires experience that connects decisions to complete outcomes. We present NorthCUA, an integrated system for turbocharging computer-use agents through experience at scale. Its Experience Flywheel supp…

🅲 hạng C
20
Order-Only On-Policy Distillation
📄 Paper HF Daily Papers 19 ngày trước

On-policy distillation (OPD) trains a student on its own generations by matching the teacher's token probabilities. These probabilities entangle two kinds of information: which tokens the teacher prefers, and how confident it is. The latter reflects the teacher's own capacity and…

🅲 hạng C
20
MoviEdit: Long-form Multi-Shot Video Editing Made Easy
📄 Paper HF Daily Papers 18 ngày trước

Long-form multi-shot video editing requires an intended edit to remain coherent across abrupt changes in scene, viewpoint, and subject appearance, while processing substantially longer visual context than conventional single-shot editors. We introduce MoviEdit, an end-to-end fram…

🅲 hạng C
20
YANAMI: A Large-Scale Multimodal Dataset and Benchmark for Multiturn Stateful Interaction
📄 Paper HF Daily Papers 17 ngày trước

Unified Multimodal Models (UMMs) integrate visual understanding, generation, and editing within a single unified framework. However, existing unified multimodal datasets and benchmarks remain dominated by single-turn tasks. Even in recent multi-turn datasets, many turns can be so…

🅲 hạng C
20
Confucius4-R2T2: A Stable-Prefix Streaming ASR Model for Real Real-Time Transcription
📄 Paper HF Daily Papers 15 ngày trước

Streaming speech recognition is increasingly consumed by machines, such as translators and voice agents, that act on each token as it appears. A token that is later revised costs wasted work or a wrong action. In this work, we present Confucius4-R2T2 (short for Real Real-Time Tra…

🅲 hạng C
20
LongBanana: An Expert-Verified Benchmark for Long-Context Multi-Reference Image Synthesis
📄 Paper HF Daily Papers 15 ngày trước

We introduce LongBanana, to our knowledge the first expert-designed and expert-verified benchmark for long-context multi-reference image synthesis in the age of agent-driven image generation. The task requires retrieving dispersed visual evidence, rejecting distractors, binding e…

🅲 hạng C
20
Self-Improvement Memory Enables Continual Recursive Self-Improvement
📄 Paper HF Daily Papers 7 ngày trước

Harness optimization is often studied with a fixed policy model and benchmark. When either changes, the optimizer must decide which parts of an evolved harness to reuse or revise, but the harness alone may not explain why earlier edits were made or how they performed. In this wor…

🅲 hạng C
20
CONGA: Compiling Gaussian Fiber Geometry for Structured Bayesian Inference
📄 Paper HF Daily Papers 4 ngày trước

In structured Bayesian models, a large latent block is often Gaussian conditional on a smaller set of parameters, yet generic inference methods relearn this geometry during warmup. We study how this structure can be used to construct transports for posterior inference. The condit…

🅲 hạng C
20
ReLift: Dense 3D Tracking as Lifted Trajectory Repair
📄 Paper HF Daily Papers 20 ngày trước

Dense 3D tracking from monocular video requires establishing point correspondences over time, estimating their depth, and inferring their trajectories during occlusion. Existing methods typically learn these tasks jointly, a demanding objective given the scarcity of 4D supervisio…

🅲 hạng C
20
Venus-DefakerOne2: A Vision-Forensics Foundation Model with Broader Coverage
📄 Paper HF Daily Papers 24 ngày trước

Real-world forgery is inherently heterogeneous: it manifests not only as digital manipulation but also as physical spoofing, and is carried not only by images but also by videos. Despite substantial progress, a unified anti-forgery foundation model covering such a broad threat sp…

🅲 hạng C
20
From Fragmentation to Fusion: A Survey and Roadmap for Omnimodal Embeddings
📄 Paper HF Daily Papers 21 ngày trước

Embedding models underpin virtually every modern AI system, from search engines to recommendation systems. Despite shared mathematical foundations, research on embedding models remains fragmented by modality: the communities develop largely in isolation, seldom exchanging insight…

🅲 hạng C
20
When Does Latent Prediction Error Support Physical Surprise Claims in Video World Models?
📄 Paper HF Daily Papers 18 ngày trước

Prediction errors from video world models are often treated as physical surprise, but they can also reflect appearance, static content, motion, or ordinary prediction difficulty. We present an evaluation framework that separates what frozen representations contain, how they organ…

🅲 hạng C
20
RoboColosseum: Evaluating Physical Intelligence at Scale In-The-Wild
📄 Paper HF Daily Papers 18 ngày trước

General-purpose robot policies must work across robots, tasks, and environments, yet the variation that makes physical trials informative also makes them difficult to reproduce. We introduce RoboColosseum, a distributed evaluation framework that combines unified policy serving an…

🅲 hạng C
20
VisSearch-Bench: Evaluating Long Horizon Visual Search in Multimodal Agents
📄 Paper HF Daily Papers 17 ngày trước

Multimodal agents use web and image tools to answer questions beyond their internal knowledge. Some search tasks use images mainly to identify an initial entity, then rely on text retrieval. These tasks offer limited insight into how agents connect information across images, obje…

🅲 hạng C
20
MMDM: Measuring Massive Multitask Decision Making
📄 Paper HF Daily Papers 10 ngày trước

System-1 Decision Models directly make structured probabilistic decisions over query-specified options given a state in a single forward pass, without autoregressively generating reasoning trajectories or textual responses. Recent evaluations cover diverse tasks but often rely on…

🅲 hạng C
20
DexForesight: Grounding Dexterous Policies with Implicit Spatial Foresight
📄 Paper HF Daily Papers 10 ngày trước

Dexterous manipulation requires rich spatial foresight over both the surrounding scene and the robot hand. Existing world-action models often acquire such predictive knowledge through explicit future prediction. We introduce DexForesight, a framework that learns spatial foresight…

🅲 hạng C
20
TTB: Test-time Baking for Efficient Rendering of Decoder-only View Synthesis Models
📄 Paper HF Daily Papers 8 ngày trước

Decoder-only Large View Synthesis Models (LVSMs) with KV-cache have recently achieved state-of-the-art quality by regressing novel views from neural networks without reconstructing 3D geometry, while Test-Time Training (TTT) layers save computation but sacrifice quality. We propo…

🅲 hạng C
20
PaperCritic: Training AI Reviewers to Assess the Soundness of Papers
📄 Paper HF Daily Papers 7 ngày trước

As AI conference submissions grow rapidly, AI reviewers are being considered as an alternative. However, simply imitating human reviewing is problematic because reviewing serves multiple purposes, including evaluating papers' soundness, interestingness, and clarity, the last two …

🅲 hạng C
20
DiscoDemo: Discovering Efficient and Diverse Robot Demonstrations for Imitation Learning
📄 Paper HF Daily Papers 28 ngày trước

Behavior cloning for robotic manipulation is highly sensitive to the coverage of its training data, yet collecting diverse successful demonstrations remains costly. We study reinforcement learning (RL) not as a deployable controller, but as a data generator for downstream visuomo…

🅲 hạng C
20
World-in-Context: Interactive Video World Modeling with In-Context Conditioning
📄 Paper HF Daily Papers 28 ngày trước

Interactive video world models require coordinated control over viewing perspectives, character actions, and camera motion. Existing methods typically leave view modes implicit in text captions, conflate action with camera motion, and inject controls through fragmented architectu…

🅲 hạng C
20
Channel Selection for Mixture-of-Experts Decoding Needs No Calibration Data
📄 Paper HF Daily Papers 24 ngày trước

Mixture-of-Experts (MoE) models are bottlenecked by loading routed-expert weights from memory during interactive decoding at small batch sizes. Because most intermediate channels in a routed expert contribute little to any single token, channel selectors predict which channels ma…

🅲 hạng C