🔥 JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting

💡 The paper introduces JetSpec, a speculative decoding framework designed to improve the inference speed and acceptance rates of large language models. The problem addressed is the scaling limitation of speculative decoding, which accelerates autoregressive large language models by drafting multiple tokens and verifying them in parallel. However, increasing the draft budget only improves speed when acceptance remains high and drafting overhead stays low, creating a scaling ceiling.

The proposed JetSpec framework combines efficient forward drafting with causal conditioning to break this ceiling. It trains a causal parallel draft head over fused hidden states from the frozen target model, producing candidate trees whose scores align with the target model's autoregressive factorization. This approach enables JetSpec to convert larger draft budgets into longer accepted prefixes and higher end-to-end speedup.

The method is compared to bidirectional-head and tree-based speculative decoding baselines across various benchmarks, including math, coding, and chat tasks on dense and MoE models. The results show that JetSpec consistently outperforms these baselines, achieving significant speedup on different workloads. Specifically, JetSpec achieves up to 9.64x speedup on math tasks and 4.58x on open-ended conversational workloads, with further latency gains demonstrated through integration with virtual large language models under realistic serving loads.

Overall, the paper contributes a novel speculative decoding framework that breaks the scaling ceiling of prior methods, enabling faster and more efficient large language model inference. The code and models are made available for further research and development.

📅 Published on Jun 25

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2606.18394
• PDF: https://arxiv.org/pdf/2606.18394
• Project Page: https://jetspec-project.github.io/jetspec-web/

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#SpeculativeDecoding #LargeLanguageModels #AutoregressiveModeling #ParallelTreeDrafting #CausalConditioning

🔥 OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning

💡 The paper proposes a framework called On-Policy Skill Distillation, or OPID, which aims to improve the efficiency and performance of language agent training in reinforcement learning. The problem addressed is that outcome-based reinforcement learning provides sparse rewards that do not offer sufficient guidance on intermediate decisions, while existing self-distillation methods often rely on external skill memories that can be costly to maintain and may not match the current policy.

OPID addresses this issue by extracting skill supervision directly from completed on-policy trajectories, representing trajectory hindsight as hierarchical skills that capture both global and local decision knowledge. The framework uses a critical-first routing mechanism to select the most relevant skill and inject it into the interaction history, allowing the old policy to re-score responses under both original and skill-augmented contexts. This yields a token-level self-distillation advantage that is combined with the outcome advantage for policy optimization.

The results of the experiments demonstrate that OPID generally improves agent performance, sample efficiency, and robustness over outcome-only reinforcement learning and existing skill-distillation baselines. The framework preserves reinforcement learning as the primary training objective while introducing dense, distribution-matched hindsight supervision. The experiments were conducted on several datasets, including ALFWorld, WebShop, and Search-based QA, and the code is available for further research. Overall, OPID offers a novel approach to skill distillation that can enhance the training of language agents in reinforcement learning.

📅 Published on Jun 25

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2606.26790
• PDF: https://arxiv.org/pdf/2606.26790

🤖 Models citing this paper:
• https://huggingface.co/Jinyang23/OPID-ALFWorld-1.7B

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#AgenticReinforcementLearning #OnPolicyLearning #SkillDistillation #ReinforcementLearningFrameworks #HierarchicalReinforcementLearning

🔥 Terrain Diffusion: A Diffusion-Based Successor to Perlin Noise in Infinite, Real-Time Terrain Generation

💡 The paper introduces Terrain Diffusion, a new method for generating realistic and infinite procedural worlds in real-time. The current method, Perlin noise, is fast and infinite but lacks realism and large-scale coherence. Terrain Diffusion uses diffusion models and a novel algorithm called InfiniteDiffusion to address these limitations. The InfiniteDiffusion algorithm enables seamless and real-time synthesis of boundless landscapes by coupling planetary context with local detail through a hierarchical stack of diffusion models. The method also uses a compact Laplacian encoding to stabilize outputs across large dynamic ranges and an open-source infinite-tensor framework to support constant-memory manipulation of unbounded tensors. Additionally, few-step consistency distillation enables efficient generation. The results show that Terrain Diffusion can synthesize entire planets coherently, controllably, and without limits, making it a practical foundation for procedural world generation. The method provides constant-time random access, seamless infinite extent, and seed-consistency, making it a suitable successor to Perlin noise. Overall, the paper presents a significant contribution to the field of procedural world generation, enabling the creation of realistic and infinite worlds in real-time.

📅 Published on Dec 9, 2025

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2512.08309
• PDF: https://arxiv.org/pdf/2512.08309
• Project Page: https://xandergos.github.io/terrain-diffusion/

🤖 Models citing this paper:
• https://huggingface.co/xandergos/terrain-diffusion-30m
• https://huggingface.co/xandergos/terrain-diffusion-90m
• https://huggingface.co/xandergos/TerrainDiffusion-Consistency-Base-192x3

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#ProceduralTerrainGeneration #InfiniteWorlds #DiffusionModels #RealTimeTerrainSynthesis #PerlinNoiseAlternatives

🔥 Hallucination in World Models is Predictable and Preventable

💡 The paper addresses the issue of hallucination in world models, which occurs when the model generates unrealistic futures despite appearing visually fluent. The authors hypothesize that hallucination happens in low-data regions of the state-action space and can be detected and mitigated using data-centric signals and coverage-aware sampling techniques.

To test this hypothesis, the authors created a large dataset called MMBench2, consisting of 427 hours of data and 210 tasks for visual world modeling, with ground-truth actions and rewards. They trained a 350M-parameter world model on this dataset and identified three distinct modes of hallucination: perceptual, action-marginalized, and scene-diverging.

The authors developed three signals that can accurately predict where the model will fail and used these signals to develop a coverage-aware sampling technique to close coverage gaps during training. They also used the hallucination predictors as curiosity rewards for targeted data collection to adapt the pretrained world model to new environments with as few as 50 real environment trajectories.

The results show that hallucination in world models is indeed a data coverage issue and that the same signals used to detect it can also be used for mitigation. The authors provide a data-efficient finetuning recipe that can adapt the pretrained world model to entirely unseen environments, demonstrating the effectiveness of their approach. Overall, the paper contributes to a better understanding of hallucination in world models and provides a practical solution to prevent and mitigate it.

📅 Published on Jun 25

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2606.27326
• PDF: https://arxiv.org/pdf/2606.27326
• Project Page: https://www.nicklashansen.com/mmbench2

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#HallucinationInAI #WorldModelingTechniques #PredictiveModelingForRobotics #DataCentricSignalProcessing #VisualWorldModeling

🔥 Geometric Context Transformer for Streaming 3D Reconstruction

💡 The paper presents a new approach to streaming 3D reconstruction, which involves recovering 3D information such as camera poses and point clouds from a video stream. This task requires geometric accuracy, temporal consistency, and computational efficiency. To address this problem, the authors introduce LingBot-Map, a feed-forward 3D foundation model that uses a geometric context transformer architecture. The key component of this architecture is a specialized attention mechanism that integrates three main elements: an anchor context, a pose-reference window, and a trajectory memory. These elements work together to address coordinate grounding, dense geometric cues, and long-range drift correction, allowing the model to maintain a compact streaming state while retaining rich geometric context. The result is a model that can perform stable and efficient inference at around 20 frames per second on high-resolution inputs, even over long sequences exceeding 10,000 frames. The authors evaluate their approach on various benchmarks and demonstrate that it outperforms both existing streaming and iterative optimization-based methods, achieving superior performance in terms of geometric accuracy and temporal consistency. Overall, the paper contributes a novel and effective approach to streaming 3D reconstruction, with potential applications in areas such as robotics, computer vision, and virtual reality.

📅 Published on Apr 15

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2604.14141
• PDF: https://arxiv.org/pdf/2604.14141
• Project Page: https://technology.robbyant.com/lingbot-map

🤖 Models citing this paper:
• https://huggingface.co/robbyant/lingbot-map
• https://huggingface.co/agramoi/lingbot-map
• https://huggingface.co/maujim/lingbot-map-long-only

🚀 Spaces citing this paper:
• https://huggingface.co/spaces/limonsyrah/lingbot-3d
• https://huggingface.co/spaces/mohan007/lingbot-3d
• https://huggingface.co/spaces/Fifthoply/lingbot-3d-ZERO

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#GeometricDeepLearning #3DReconstructionAlgorithms #StreamingComputerVision #TransformerArchitectures #PointCloudProcessing

🔥 The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning

💡 The paper introduces a large scale dataset collection called The Well which provides diverse numerical simulations for machine learning models in physical systems simulation. The problem addressed is that standard datasets in this space often cover small classes of physical behavior making it difficult to evaluate the efficacy of new approaches. To address this gap the authors created The Well which is a collection of datasets containing numerical simulations of a wide variety of spatiotemporal physical systems. The dataset draws from domain experts and numerical software developers and provides 15 terabytes of data across 16 datasets covering diverse domains such as biological systems fluid dynamics acoustic scattering and magneto hydrodynamic simulations. The authors also provide a unified PyTorch interface for training and evaluating models to facilitate usage of The Well. The dataset and code are available for use and the authors demonstrate the function of the library by introducing example baselines that highlight the new challenges posed by the complex dynamics of The Well. The main contribution of the paper is the creation of a large scale diverse dataset that can be used to benchmark machine learning models in physical systems simulation and provide a more comprehensive evaluation of their efficacy.

📅 Published on Nov 30, 2024

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2412.00568
• PDF: https://arxiv.org/pdf/2412.00568

📊 Datasets citing this paper:
• https://huggingface.co/datasets/polymathic-ai/acoustic_scattering_inclusions
• https://huggingface.co/datasets/polymathic-ai/rayleigh_benard
• https://huggingface.co/datasets/polymathic-ai/planetswe

🚀 Spaces citing this paper:
• https://huggingface.co/spaces/polymathic-ai/TheWell

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#PhysicsSimulations #MachineLearningModels #PhysicalSystemsSimulation #NumericalSimulations #SpatiotemporalData

🔥 olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models

💡 The paper presents olmOCR, an open source toolkit that uses a fine tuned vision language model to extract clean text from PDF documents while preserving their structure. The problem addressed is that PDFs come in diverse formats and visual layouts, making it challenging to extract and represent their content for language model use. The method involves using a 7 billion parameter vision language model trained on a sample of 260,000 pages from over 100,000 crawled PDFs with diverse properties. The model is fine tuned to process PDFs into clean linearized plain text in natural reading order, preserving structured content such as sections, tables, lists, and equations. The results show that olmOCR is optimized for large scale batch processing, able to scale flexibly to different hardware setups, and can convert a million PDF pages for a relatively low cost of 190 USD. The toolkit is released as open source, including the vision language model weights, data, training code, and inference code, making it accessible for use in training language models with the trillions of tokens available in PDF documents. Overall, the paper contributes a scalable and cost effective solution for unlocking the content of PDF documents, which can be used to train high quality language models.

📅 Published on Feb 25, 2025

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2502.18443
• PDF: https://arxiv.org/pdf/2502.18443
• Project Page: https://olmocr.allenai.org/

📊 Datasets citing this paper:
• https://huggingface.co/datasets/allenai/olmOCR-bench
• https://huggingface.co/datasets/shhdwi/olmocr-pre-rendered
• https://huggingface.co/datasets/Voxel51/olmOCR_bench

🚀 Spaces citing this paper:
• https://huggingface.co/spaces/davanstrien/benchmark-race
• https://huggingface.co/spaces/OpenEvals/every-leaderboards
• https://huggingface.co/spaces/OpenEvals/leaderboard-watcher

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#VisionLanguageModels #PDFTextExtraction #DocumentLayoutAnalysis #OCRTechniques #NaturalLanguageProcessing

🔥 Training Video Foundation Models with NVIDIA NeMo

💡 The paper addresses the challenges of training large scale high quality video foundation models that can generate high quality videos. Video foundation models have been used to simulate the real world and develop creative visual experiences but training them is difficult due to the complexity and size of video datasets. To overcome this the authors present a scalable open source pipeline using NVIDIA NeMo for training and inference of video foundation models. The pipeline provides accelerated video dataset curation multimodal data loading and parallelized video diffusion model training and inference. The authors also provide a comprehensive performance analysis highlighting best practices for efficient video foundation model training and inference. The pipeline is designed to address the challenges of training large scale video foundation models and provides a scalable and efficient solution for generating high quality videos. The results of the paper demonstrate the effectiveness of the pipeline in training video foundation models and provide insights into the best practices for efficient training and inference. Overall the paper contributes to the development of video foundation models by providing a scalable and efficient pipeline for training and inference.

📅 Published on Mar 17, 2025

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2503.12964
• PDF: https://arxiv.org/pdf/2503.12964

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#VideoFoundationModels #NVIDIANeMo #VideoDatasetCuration #MultimodalLearning #VideoDiffusionModels

💥 #Cisco Certification Journey Starts Here!
Want to become a certified Network Engineer and boost your IT career in 2026? 🚀
Whether you're preparing for #CCNA #CCNP or even #CCIE, this is your chance to get premium Cisco learning resources & insider study support!

🔥 What You’ll Get:
🌐 Cisco Training Roadmaps
🌐 Networking Lab Guides
🌐 Command Cheat Sheets
🌐 Cisco Official eBooks
🌐 Real Practice Questions
🌐 Exam Preparation Tips

🎁 FREE Starter Resources Available:
🔗✅ CCNA Beginner Notes:https://reurl.cc/j6bqey
🔗✅ CCNP Study Checklist:https://reurl.cc/npWnbn

📩 To receive all FREE Cisco materials directly in your inbox:
wa.link/8i0msc
👉 Connect us and Leave your email to get instant access!

💡 Bonus for subscribers:
https://chat.whatsapp.com/FLth69u2WswIlZ6bta2SJf
✔ Exclusive study group invitations
✔ Latest Cisco exam changes
✔ Fast-track learning strategies
✔ Priority access to upcoming training sessions

⚡ Thousands of IT learners are already preparing smarter.
Don’t miss your chance to level up your networking career in 2026! 🚀

🔥 Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

💡 The paper introduces Agents-A1, a 35 billion parameter Mixture-of-Experts Agentic Model that achieves performance comparable to trillion-parameter models by scaling the agent horizon instead of the parameters. The problem addressed is how to improve the performance of large language models on long-horizon tasks without increasing the number of parameters. The method used is a three-stage training approach, which includes supervised fine-tuning, domain-level teacher models, and multi-teacher distillation. The model is trained on a long-horizon knowledge-action infrastructure that connects external knowledge, actions, observations, and verifier outcomes, producing agentic trajectories with an average length of 45,000 tokens. The results show that Agents-A1 achieves strong and broad performance on long-horizon agent benchmarks, outperforming or matching the results of 1 trillion parameter models on several tasks, including SEAL-0, IFBench, HiPhO, FrontierScience-Olympiad, and MolBench-Bind. The paper provides a practical path for scaling the horizon using a smaller model that can reach or match the performance of larger models on long-horizon tasks.

📅 Published on Jun 29

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2606.30616
• PDF: https://arxiv.org/pdf/2606.30616
• Project Page: https://internscience.github.io/Agents-A1/

🤖 Models citing this paper:
• https://huggingface.co/InternScience/Agents-A1
• https://huggingface.co/InternScience/Agents-A1-FP8-dynamic
• https://huggingface.co/Abiray/Agents-A1-Q4_K_M-GGUF

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#MixtureOfExperts #AgenticModels #LongHorizonTasks #LargeLanguageModels #ParameterEfficientTraining