머신러닝 최신 연구, 코드와 함께.
Trending 지금 뜨는 연구
HF 업보트 · GitHub 스타 · 공개 구현 수 기준
OmniEdu: Open Foundation Models for Learning and Teaching
Educational foundation models must solve problems, understand curriculum structure, diagnose learner difficulties, and provide appropriate instructional support. Existing educational language models often focus on either…
Training Object Permanence in World Models
Object permanence and solidity are hallmarks of human cognitive priors. Recent studies show that video generation models, a paradigmatic class of current world models, have begun to show emerged reasoning abilities, maki…
Video GenerationRRSI: Regularized Recursive Self-Improvement of Agent Harnesses
An LLM agent's capability is largely magnified by its harness, namely the prompts, control flow, tooling, memory, and context management surrounding the frozen backbone model. Recent methods increasingly automate this pr…
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
The widespread adoption of long-horizon agents has made model workloads increasingly input-heavy. Although prior work has substantially reduced the cost of long-context computation, prefill remains computationally expens…
Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability
On-Policy Distillation (OPD) trains a student on its own generations using teacher feedback. With different tokenizers, comparing teacher and student predictions requires alignment at both sequence and vocabulary levels.…
Mathematical ReasoningCode GenerationThe Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks
LLM agents increasingly work on long-horizon tasks, and the decisions they make along the way, such as which hypothesis to test or which implementation to build on, determine the outcome of the whole run. Making these de…
WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory
Video world models enable interactive exploration of dynamic environments, yet struggle to respect prior observations over long horizons and across viewpoints. We present WorldCrafter, a video world model that learns a c…
GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay
Modern video games provide a measurable testbed for AI models, combining abilities of visual understanding, instruction decomposition, goal planning, and precise action control over multiple temporal horizons. Existing d…
Can MiniMax-H3 Reason About the Physical World? An Evaluation of Omni-Modal Generative Model
Recent Omni-Modal Generative Models (Omni-Models) have advanced content generation toward unified modeling of text, images, video, and audio. MiniMax-H3 exemplifies this transition by combining multimodal context underst…
Video GenerationYuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality
Symbolic models make melody, harmony, rhythm, and form explicit but typically stop before a finished recording; audio models produce complete songs while leaving composition implicit. We introduce YuE2, which unifies sym…
Representation LearningMusic GenerationLatest 최신 논문
We Query, Therefore We Compute: On Oracle Computation beyond the Machine, with an Application to Agents
Agentic systems use large language models (LLMs) to carry out concrete tasks. Prior work often borrows abstractions such as scheduling, caching or isolation piecemeal from operating systems, so the mechanisms it builds s…
RLHND: Video Foundation Models as Physically Grounded Hand Trackers for Robot Learning
Recently, approaches that leverage human video datasets for robot policy training have become increasingly prevalent. However, most existing hand trackers regress pose from cropped frames with limited priors on hand moti…
Pose EstimationWebFovea: When the Model Is Right but the Click Is Wrong -- Reliable Round Trips for Vision-Based Web Agents on Live Websites
We present WebFovea, a vision-based web agent that placed 2nd in the WebRetriever Challenge 2026 with a final score of 57.0 out of 100. The challenge evaluates agents end to end on Protocol III of the WebRetriever benchm…
Mechanics of Long-Context Hybrid Models Part 1.1: From Hybrid Attention to Hybrid Position
The architectural design of Large Language Models (LLMs) is shifting from traditional full-attention-only models to hybrid models, which combine different attention modules to improve long-context efficiency and performa…
Continual PretrainingAdSpark: A Large-Scale Dataset and Benchmark for Product-Centric Advertisement Video Generation
Product-centric advertisement video generation aims to create promotional videos that preserve fine-grained product identity while presenting selling points through coherent multi-shot narratives. However, this emerging …
Visual StorytellingVideo GenerationSGF+: Decoupling Gradient Flows for Autoregressive Video Generation
Autoregressive video generation requires denoising the current frames while writing their key-value representations as context for future predictions. However, these two roles typically share parameters, and we find that…
Video GenerationInverting Multi-Vector Visual Document Indices
Prevailing multi-vector visual document retrievers store each page as about a thousand patch vectors, often in vector databases run by a third party. Since no one can read a page from its vectors, this index is easily tr…
Image GenerationLong-WAM: Scaling the Context of World-Action Models
Real-time robot control demands enough visual history to infer motion and task progress, but processing that history can delay action. We present Long-WAM, a model-system framework for scaling the context of causal world…
GRACE: Generation-aware latent compression for efficient video generation
Highly compressed video autoencoders offer an effective way to accelerate video diffusion models, as the Diffusion Transformer (DiT) operates on far fewer tokens. However, such autoencoders are challenging to train, sinc…
Video GenerationUltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation
Dense visual text requires image generators to reproduce long strings across multiple regions with correct placement and legibility. As short-string rendering improves, evaluation must test sustained performance across m…
Image GenerationRoboQuest: Generalist Physical Agents that Search, Inspect and Test
Recent advances in multimodal foundation models have made them capable generalist physical agents for a range of manipulation tasks. However, successful operation in an unfamiliar environment may require an agent to seek…
RobotWorld: Benchmarking Multimodal Agents for Robot Use Across Diverse Tasks and Embodiments
General-purpose agents increasingly write code, use tools, and complete complex digital tasks, raising the question of how far these capabilities carry into the physical world. To investigate this, we introduce RobotWorl…
Image SegmentationRunningTab: Direct Workspace Interaction with Environment-Side Tabs
Much knowledge work produces new deliverables from files a workspace already holds, and LLM agents are beginning to take such work over. Through direct corpus interaction, an agent can search and read any of those files …
SWE-Game: Can Coding Agents Build the Games We Want?
We introduce SWE-Game, a benchmark of 247 tasks grounded in 41 executable reference Godot games spanning 13 gameplay categories in 2D and 3D. Five task types cover development from a brief, implementation from a game des…
Tetris3D: 3D Scene Generation With Objects That Fit Together
We propose Tetris3D, a generative framework for single-image 3D scene reconstruction that recovers objects which are physically and geometrically coherent as a scene. Existing methods often generate objects independently…
Scene GenerationTRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models
Reinforcement learning (RL) for post-training large language models (LLMs) incurs substantial computation and memory overhead during rollout generation, which motivates low-precision rollout for efficient RL training. Ho…
Reinforcement LearningAdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model
Web agents complete user requests by reading and acting on pages that third parties write, so an instruction planted on a page can redirect the agent away from the user's goal. The agent cannot simply ignore the page, be…
From Evidence to Action: How Tool-Using Agents Fail
Tool-using agents make consequential changes to external state, yet correct outcomes do not guarantee that their actions were supported by evidence established beforehand. We study where this evidence-to-action chain bre…
Action AssessmentTowards In-Parameter Memory Augmentation for Large Language Models
Recently Large Language Models (LLMs) and LLM-based agents increasingly need to incorporate knowledge acquired after pretraining, e.g., domain facts, user preferences, documents, and interaction experience. In-context le…