Weekly Digest 2026년 41주차
2026-10-05 ~ 2026-10-11 신규 논문 91편을 분야별로 묶었습니다. 정렬: 인기 신호(HF 업보트·GitHub 스타·구현 수).
General 49편
Long-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…
nanoMuse: An Open-Source Personal Agent for Every Device You Own
Assistants from 2011 answered and waited, and agents from 2023 did a task and stopped. In September 2026 Meta's Muse showed an agent for one person, with accounts, devices, memory and a conversation that lasts, closed, i…
DecepEval: A Benchmark for Evaluating Deception in LLM Agents
As large language model (LLM) agents become increasingly autonomous, they may pursue task performance through deception, raising concerns about their reliable deployment. Existing evaluations show that LLM agents can dec…
WorldSonus: Bringing Sound to Worlds
Recent advances in world models have enabled increasingly realistic visual synthesis. However, these generated environments remain largely silent. Bringing sound to world models poses three core challenges: real-time gen…
Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness
Recent game design agents have made substantial progress in generating playable games. However, program correctness does not ensure an enjoyable experience for players. We present Recursive Game Creator, an experience-or…
Representation-Space MMD for Diffusion Language Models
We introduce a post-training method for diffusion language models (DLMs) that minimizes Maximum Mean Discrepancy (MMD) between generated and reference distributions in the feature space of a frozen pretrained DLM. To est…
Optimizing the Optimizer: Language Models Discover Faster Molecular Relaxation
Geometry optimization is a major cost in many quantum-chemical workflows: each optimization step requires one force evaluation, and at the density-functional level that evaluation dominates the wall time. Research in thi…
MiniCorp: The Last Mile of the AI Agent Firm
The last mile toward enterprise AGI is a company that runs itself. Training and adapting such agents require longitudinal enterprise data, which remain scarce, costly to acquire, and often restricted by privacy constrain…
Methodology 20편
TRACE: 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 LearningHuatuoGPT-3: RL-Only Domain Adaptation from Base Models
Domain adaptation aims to turn a general-purpose large language model (LLM) into an expert for a target domain. While the dominant SFT+RL pipeline offers a convenient cold start, it may reduce exploration diversity and i…
Domain AdaptationTowards Looped Models Done Right, Part II: Rethinking at Fixed Points
Every recurrence of a looped language model adds cost in training, decoding, prefill, and reinforcement learning (RL). The closer recurrent states get to fixed points, the less the path to them matters. This enables trun…
Reinforcement LearningTRIAGE: Direction-Aware Mismatch Stabilization of Native NVFP4 Reinforcement Learning
Low-precision execution can substantially accelerate reinforcement learning (RL) for large language models, but discrepancies between learner and sampler execution can destabilize policy optimization. In this paper, we c…
Reinforcement LearningMathematical ReasoningMechanics 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 PretrainingOn KL-Regularized Policy Optimization
Asynchronous reinforcement learning (RL) for large language model (LLM) agents trains one policy on trajectories generated by another: rollouts come from stale checkpoints, and the inference engine's probabilities differ…
Reinforcement LearningMinimal Witness Reinforcement Learning
``What are the irreducible conditions that are sufficient to produce an outcome?'' is one of the most common questions that recur across computation and science. Its answers, the minimal sufficient witnesses, are what we…
Reinforcement LearningBase Models Can Reason By Taking a Cue From Training Data
In this paper, we study how training data creates associations between the tokens at the start of a base model's response and the reasoning behavior that follows. First, we demonstrate that fixing particular starting tok…
Reinforcement LearningComputer Vision 8편
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 AssessmentTetris3D: 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 GenerationEmbodiedSmith: Scaling Embodied Data through Recursive Self-Improvement Flywheel in Simulation
Scaling robotic foundation models requires diverse training data and reliable evaluation environments. Simulation offers a scalable solution, yet existing generation pipelines remain constrained by predefined assets and …
Scene GenerationRobotWorld: 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 SegmentationBuilding Rome from a Single Image
Single-image scene generation aims to produce a complete 3D scene mesh from a single image, including surfaces the camera did not observe. While pretrained 3D object generators encode a strong shape prior, they are mainl…
Scene GenerationRLHND: 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 EstimationJLD: Perceptual Distance Through A Jacobian Lens
Image compression, restoration, and generation all require a way to measure how different two images look to a person. Pixel error ignores how people see, while the most accurate perceptual distances are typically fitted…
Image CompressionWildMatch: Weakly Supervised Image Matcher Adaptation for Wildlife Re-Identification
Individual animal re-identification from camera-trap imagery is an instance retrieval problem central to non-invasive wildlife monitoring: a query image must retrieve the correct individual from a reference set of known …
Image MatchingNatural Language Processing 5편
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 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 GenerationAdSpark: 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 GenerationRealtimeWAM: One-Step Asynchronous World Action Models
World Action Models (WAMs) incorporate visual representations from video generation backbones to guide action prediction. Recent efficient WAMs adopt Mixture-of-Transformers (MoT) architectures and compute video represen…
Video GenerationWorld Models' Last Exam in Physics
Video world models can produce visually convincing yet physically inconsistent sequences, raising concerns about their reliability for prediction and planning in embodied AI systems. Existing evaluations often rely on mo…
Video GenerationKnowledge Base 2편
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 GenerationTechnical Report on the Turba Fertilizer Machine Learning Stack in Morocco
Site-specific fertilizer recommendation systems adapt nutrient advice to location, soil properties, crop type, and production targets, but scientific reuse is constrained when recommendation functions remain accessible m…
Recommendation SystemsMedical 2편
Inverting 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 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 GenerationMiscellaneous 1편
CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?
Static-analysis checker synthesis requires agents to interpret a defect specification, inspect a repository, implement analyzer-specific logic, and refine the checker through repeated compilation and analysis feedback. E…
Vulnerability DetectionRobots 1편
VeriFine: Scaling Verification for Self-Improvement in Embodied Reasoning
Self-improving policies continually expose new failure patterns, changing what their judges must be able to verify. However, current fixed judges constrain both optimization feedback and the discovery of useful training …
Robot NavigationAudio 1편
Hiding Tool Latency in On-Device Cascaded Voice Agent through Speculative Execution
Tool-augmented speech assistants typically serialize automatic speech recognition, large language model inference, and external tool execution. As a result, tool latency is incurred only after the user has finished speak…
Speech RecognitionComputer Code 1편
S2PD: Serial-to-Parallel Diffusion for Physically and Logically Consistent Video Generation
Bidirectional video diffusion models denoise entire videos in parallel, yet when trained on effectively unlimited in-distribution data from procedural generators, continue to violate physical laws and simple symbolic rul…
Physical SimulationsVideo GenerationTime Series 1편
Conditional Trajectory Peaks: Single-Pass Multimodal Policies over Action Chunks
Multimodal imitation learning requires diverse executable futures under the same observation and consistent behavior across replanning cycles. We present Conditional Trajectory Peaks (CTP), a single-pass policy framework…
Trajectory Modeling