cập nhật 33 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.6 giờ sau khi CVE được công bố (n = 5196, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

0
Micius-Flash: Lightweight Agentic Intelligence for Engineering
📄 Paper HF Daily Papers 17 ngày trước

We introduce Micius-Flash, a 27-billion-parameter model for engineering with native multimodal input, deep reasoning and a 256K-token context window. We design the Micius data pipeline as a knowledge-tree-driven data flywheel comprising three stages: knowledge tree construction a…

🅲 hạng C
0
DyCraft: An Agentic System for Long-Horizon 4D Scene Generation
📄 Paper HF Daily Papers 23 ngày trước

While frontier coding agents can generate high-quality 3D scenes and articulated assets, they struggle to create coherent long-horizon animations. When equipped with general-purpose harnesses, they frequently produce physically implausible outputs, generating objects that interpe…

🅲 hạng C
0
Incentivizing Self-Learning in Large Language Models via Reinforcement Learning
📄 Paper HF Daily Papers 23 ngày trước

Large language models (LLMs) draw on parametric knowledge and retrieval-augmented generation (RAG) to solve knowledge-intensive tasks. Yet problem solving in unfamiliar domains calls for tightly coupled knowledge acquisition and reasoning, beyond factual retrieval and aggregation…

0
Scaling Mathematical Proof Supervision from Structured Textbooks
📄 Paper HF Daily Papers 23 ngày trước

Mathematical supervision for language models is typically flattened into isolated problem-solution pairs, discarding the curricular organization and evidential structure of the original sources. We introduce TOME-Math (Textbook-Oriented Mathematical Evidence), a large-scale corpu…

0
Module-Aware Optimization for Graph Neural Networks
📄 Paper HF Daily Papers 16 ngày trước

Different optimizers impose different geometries on parameter updates. Adaptive methods such as Adam and AdamW use coordinate-wise updates, while matrix-aware optimizers such as Muon utilize weight-matrix structure through orthogonalized updates. For Graph Neural Networks (GNNs),…

🅲 hạng C
0
Subliminal Learning in Vision-Language Models
📄 Paper HF Daily Papers 17 ngày trước

Subliminal learning is a phenomenon in large language models (LLMs) where a teacher passes a hidden preference to a student through training data unrelated to that preference. We study whether subliminal learning also occurs in vision-language models (VLMs). We finetune a teacher…

🅲 hạng C
0
On the Design of Hyper-Connections: Simplification, Stability, and Scalability
📄 Paper HF Daily Papers 17 ngày trước

Hyper-Connections (HC) architectures are increasingly adopted in frontier language models, yet their components remain insufficiently understood and introduce non-negligible training overhead. In this work, we systematically study the HC architecture to understand its components …

🅲 hạng C
0
Do Multimodal Models Decide Consistently on Equivalent Optical Spectra?
📄 Paper HF Daily Papers 22 ngày trước

A spectrum can be given to a model as a table in nanometers or as a plot in photon energy, and the decision should not depend on which one it sees. When the data needed for an answer are missing, the model should say so. We test representation invariance and abstention on measure…

0
Humanized but Still True? Auditing Facts and Detection in AI-Text Humanizers
📄 Paper HF Daily Papers 22 ngày trước

AI "humanizers" rewrite machine-generated text so that detectors classify it as human-written. Public leaderboards score evasion and embedding similarity, but not whether checkable details survive. We check whether numbers, dates, person and organization names, and quoted spans s…

0
Agent-R^2: Scaling Agents for Realistic Productivity Work via Real-Source Data Synthesis
📄 Paper HF Daily Papers 16 ngày trước

Large language models have made rapid progress in agentic reasoning and tool use, raising expectations for agents that can take over realistic productivity work from humans. However, current agents still struggle to finish such tasks, where success requires following long-horizon…

🅲 hạng C
0
TurtLES: A Large-Scale Benchmark for Turbulent 3D Neural PDE Surrogates
📄 Paper HF Daily Papers 15 ngày trước

Machine-learning surrogates are increasingly used to accelerate computational fluid dynamics, yet progress is limited by the lack of benchmarks capturing realistic, time-dependent turbulent flows. We introduce TurtLES, a 14 TB dataset of 3D turbulent cylinder wakes in the shear-l…

🅲 hạng C
0
GH-AWTrace: A Large-Scale Dataset of GitHub Agentic Workflow Execution Logs
📄 Paper HF Daily Papers 16 ngày trước

Agentic workflows enable AI agents to perform recurring repository tasks on schedules or in response to repository events. Existing studies examine workflow definitions and outputs, but provide limited evidence of what happens during execution. We present GH-AWTrace, a dataset li…

🅲 hạng C
0
Loopback Transformer: Towards a Unified View of Residual Looped Transformers
📄 Paper HF Daily Papers 17 ngày trước

Looped Transformers reduce parameter count by repeatedly applying shared blocks, but parameter sharing alone does not determine how the results of repeated computation are reused. We take the depth-memory view of residual connections and analyze which representation is stored aft…

🅲 hạng C
0
MIRIX-2.0: Multi-Agent Memory System
📄 Paper HF Daily Papers 12 ngày trước

Long-term memory lets LLM agents personalize, stay consistent, and reuse what worked before. Parametric memories need training, consolidation can lose details for good, and keeping every record leaves a growing store to search. We present MIRIX-2.0, a multi-agent memory system de…

🅲 hạng C
0
Re-Search: Dissecting LLM Ideation Through a Two-Player Questioning Game
📄 Paper HF Daily Papers 11 ngày trước

Research ideation is iterative: researchers refine their ideas step by step based on feedback. Yet existing evaluations obscure this search process, making it difficult to understand how LLMs explore the space of research ideas and what limits their progress. We introduce Re-Sear…

🅲 hạng C
0
Ego Guidance: Enhancing Robot Policy Learning with Action-Free Human Egocentric Videos
📄 Paper HF Daily Papers 11 ngày trước

In this paper, we investigate how human egocentric videos can benefit robot policy learning without action supervision. Building on a pretrained VLM, we propose Shared Prediction on Action and Representation (SPAR), an MoT architecture in which future visual state prediction can …

🅲 hạng C
0
Zuse: A Decision Model for European Languages
📄 Paper HF Daily Papers 17 ngày trước

Decision models read a document and return a probability for each of a fixed set of options instead of generating text. Several appeared in 2026, but none has published results outside English. We describe Zuse, three decision models (4B, 9B and 27B) that train a low-rank adapter…

🅲 hạng C
0
BitDecoding-FP4: Native FP4 KV Cache Decoding via Algorithm-System Co-Design
📄 Paper HF Daily Papers 15 ngày trước

The key-value (KV) cache dominates memory capacity and bandwidth in long-context LLM serving. While 4-bit microscaling formats (NVFP4, MXFP4) shrink the cache and run attention on FP4 Tensor Cores, a fundamental gap remains between algorithmic quantization and system-aware accele…

🅲 hạng C
0
Energy-Based Reasoners: Your Recurrent Reasoner Should Be an Energy-Based Model
📄 Paper HF Daily Papers 15 ngày trước

Looping is a powerful inductive bias for reasoning. By repeatedly iterating a recurrent block, looped models can scale their effective depth and enable multi-step reasoning in latent space. However, existing looped models are not inherently guided by an explicit measure of progre…

🅲 hạng C
0
Inside the Trading Loop: Markets, Models, and Moves with LLM Agents
📄 Paper HF Daily Papers 13 ngày trước

We built a hybrid multi-agent trading system that combines large language model (LLM) analysts with momentum-based portfolio construction and rule-based execution. Company-news and macroeconomic agents return structured reports to a coordinator that sets stock weights and cash re…

🅲 hạng C
0
Correct Labels Are Not Enough: Reliable Metadata Can Silently Control Model Behavior
📄 Paper HF Daily Papers 18 ngày trước

Fine-tuning data can include metadata that predicts the correct answer, such as a reward-model score or a quality label. We ask whether a model learns to rely on this metadata even when every training label is correct. We fine-tune 7-9B open-weight models from three families on m…

0
Breath-Dx: A Time Series Classification Benchmark for Disease Screening with eNose
📄 Paper HF Daily Papers 10 ngày trước

Electronic nose (eNose) technology offers a portable, non-invasive route for disease screening via exhaled breath analysis. However, progress in the field is hindered by the lack of systematic benchmarks that compare machine learning methods under realistic conditions, particular…

🅲 hạng C
0
Glyph: An Interpretability Engine for AI-Driven Scientific Discovery in Clinical Data
📄 Paper HF Daily Papers 15 ngày trước

Automated scientific discovery has the potential to advance understanding of disease mechanisms and accelerate identification of early disease markers. Manual data annotation is infeasible at population scale, motivating methods that automatically extract pre-defined phenotypes i…

🅲 hạng C
0
MPEG-Diffusion: Mixed-Resolution Video Generation
📄 Paper HF Daily Papers 12 ngày trước

Video diffusion transformers (DiTs) generate realistic videos, but their heavy computational cost limits broader real-world applications. Mixed-resolution generation reduces this cost by generating the visually important region at high resolution (HR) and the rest at low resoluti…

🅲 hạng C
0
The Noise Floor of a Quantization Comparison: Engine, restart, batch and kernel drift, measured against 8-bit and 4-bit effects in two decision models
📄 Paper HF Daily Papers 10 ngày trước

A quantized model is usually judged by comparing it with its BF16 original, but that comparison changes more than the weights. It often changes the serving engine, it always runs on a different server instance, it may change how requests are batched, and on some stacks the librar…

🅲 hạng C
0
Tideway: Phase-Aware Tiered Memory Management for MoE Inference on Consumer Devices
📄 Paper HF Daily Papers 11 ngày trước

Large language model (LLM) agents are rapidly becoming a dominant paradigm for AI applications. Recently, there is a growing demand to deploy large-scale Mixture-of-Experts (MoE) models locally on consumer PCs to balance data privacy, API costs, and inference efficiency. However,…

🅲 hạng C
0
LightTAR: Light and Fast Target-Aware Representations for Multimodal Tabular Learning
📄 Paper HF Daily Papers 9 ngày trước

Multimodal tabular learning involves classification and regression on tables combining structured numerical and categorical features with unstructured text and images. These unstructured fields are commonly represented by pretrained encoder embeddings reduced with principal compo…

🅲 hạng C
0
Choosing Quantized Code LLMs by File Size and Energy per Solved Task
📄 Paper HF Daily Papers 8 ngày trước

A developer running a code assistant on a laptop downloads one model file, and local inference moves the energy of every request onto that machine. A common rule says a larger model at lower precision tends to beat a smaller one at higher precision. We ran 24 GGUF files of Qwen2.…

🅲 hạng C