Minecraft Videos
βWe validate this approach using a custom dataset of long Minecraft videos, where it produces substantially more consistent rollouts compared to existing baselines.β
What the smart people are recommending. 8874 books, tools, and products endorsed by the thinkers absorb.md tracks. Ranked by how many times each has been recommended across compiled podcasts, papers, posts, and tweets.
βWe validate this approach using a custom dataset of long Minecraft videos, where it produces substantially more consistent rollouts compared to existing baselines.β
βWe introduce WebChallenger, a web agent framework that addresses each gap through architecture design rather than model scale, built around PageMem: a structured page representation deterministically β¦β
βllm.swift by @otabuzzman: a Swift port of this projectβ
βOur implementation is publicly available at https://github.com/IMSeonL/coset-ensemble-decoder.β
βWe release SWE-Marathon, evaluation code, and agent trajectories at https://swe-marathon.org/.β
βCode to reproduce the results is available at https://github.com/IlayMalinyak/mm_align_vs_pred.β
βWe introduce OncoTraj, a public benchmark of 813 EGFR-mutant NSCLC patients receiving first-line osimertinib, harmonized from three real-world clinical-genomic sourcesβ
βCode and implementation details are available at https://github.com/zachmocz/temporal-ids-benchβ
βwe adapt a discrete-token, autoregressive trajectory generator from autonomous driving (SMART) and show it yields strong best-of-20 forecasting accuracy compared to baselines, while supporting fully hβ¦β
βCode, models, and data are available at https://github.com/mahmoodphd/FADA.β
βwe found that OpenAI's o4-mini-high produced scripts that, when run on an OpenTrons liquid handling robot, successfully assembled DNA with expected sequences.β
βWe propose Flow-DPPO (Flow Divergence Proximal Policy Optimization), which replaces ratio clipping with a divergence proximal constraint.β
βwe introduce T1-Bench, a high-fidelity, comprehensive benchmark for evaluating agentic systems in realistic customer-facing, multi-domain environmentsβ
βWe introduce Data Journalist Agent (Data2Story), a multi-agent framework that orchestrates specialized roles into a single virtual newsroom.β
βOur project is available at: https://dora-explore.github.io/.β
βTo accelerate open research and deployment in Physical AI, we make our code, model checkpoints, curated synthetic datasets, and evaluation benchmark availableβ
βWe introduce SurfDesign, a surface-conditioned protein design framework that models molecular surfaces as continuous geometric manifolds and integrates them with pretrained protein language models.β
βThese results position Learn2Match as a benchmark for developing the next generation of matching-market algorithmsβ
βThe code is available on https://github.com/Hardy158118/Diffprior.β
βCode can be found at https://github.com/fraunhofer-iais/inference-framework-creditscorecards.β
βthe implementation is publicly available at https://github.com/MBamdad/HAMNOβ
βthe implementation is publicly available at https://github.com/MBamdad/HAMNOβ
βCode is available at https://github.com/robizso/slt-datagen.β
βOur code is available at https://github.com/Heinz217/GraspLLM.β
βThe source code for the proposed multi-agent design framework is available at the project GitHub repository: https://github.com/MXY820/barrier-designβ
βCodes are available at https://github.com/eeee-sys/MODF-SIRβ
βWe introduce DuoBench, an extensible benchmarking framework for bimanual manipulation policies on the FR3 Duo platform.β
βThe code can be accessed at https://github.com/atif-hassan/RCAP-dynamic-dataset-pruningβ
βCode is available at https://github.com/RSC-Toolkit/Lung-SRAD.β
βThe complete agent design code and prompts are open-sourced and can be accessed at: https://github.com/SimAgentDev/Ansys-LSPP-AgentKitβ
βOur framework, titled QLung, introduces a no-reference audio quality margin derived from spectral entropy and root-mean-square energy, which adaptively scales angular margins based on recording qualitβ¦β
βDesigned as a plug-and-play solution, CCKS integrates seamlessly with existing DTDE algorithms.β
βWe release the code and dataset at huggingface.co/datasets/neginb/OpenMedReason.β
βWe present projectmem, an open-source, local-first memory and judgment layer for AI coding agents.β
βWe have released our code at https://github.com/bebr2/SKIM .β
βCode: https://github.com/alimert05/zero-shot-stock-xaiβ
βBergson is an open source library that aims to enable faster progress in the field by providing a host of techniques that scale to very large language models and pre-training datasets.β
βWe present Open-TQ-Metal, the first implementation of fused compressed-domain attention on Apple Siliconβ
βCheckpoints and datasets are available at https://huggingface.co/collections/NebulaPixel/summorchestra-multirole-summary.β
βThe system is open-source under the MIT license.β
βThe partial MAES for the clinical scenario simulator is open sourced here.β
βThe SLBT library with the various tree-based algorithms is available in the linked GitHub repository.β
βOur code is publicly available at https://github.com/Aitorzan3/ProtoX-ADβ
βTo facilitate reproducibility, we release our code at https://github.com/kargibora/SoftElo.β
βCode: https://github.com/smitswil/craftiifβ
βWe also release SupraPMC, a curated 16M-token corpus of Supramolecular chemistry articles distilled from Europe PMC, to support the adaptation to the supramolecular domain.β
βCode is available at https://github.com/hiker-lw/MACCO.β
βThe code can be available at https://github.com/YAN-outlook/MP3β
βProject code is available at: https://github.com/minlinzeng/MOSAIC_Modality-Specific-Adaptation-for-Incremental-Continual-Learning-in-PD-Gait-Assessment.gitβ
βwe introduce \textbf{\sysname}, a \textit{stakeholder-centric} benchmark to systematically categorize and attribute harm in real-world web agent systems.β
βThe project code is available at https://github.com/DrThink-ai/CDSA-Net.β
βOur source code is available at https://anonymous.4open.science/r/NTS-CoT .β
βWe build MDForge, an LLM agent whose in-context update rule densifies the sparse reward via a multi-agent debate among physics experts.β
βOur code is available at: https://github.com/Bxzfrm/PRISM.β
βCode is available at https://github.com/TRISKEL10N/HCPD.β
βThe corresponding implementations are available in https://github.com/mahfuzmohammad/AUCp.β
βWe develop and implement these methods in pqfmlib, a publicly available Python library for constructing, executing, and benchmarking Hamiltonian-based PQFMs.β
βWe present Simplex-Constrained Sparse Bagging (SCSB), a mathematically rigorous framework for post-training compression and probability calibration of bootstrap-based bagging ensembles.β
βCode will be available at https://github.com/Wang-ML-Lab/OrchRM.β
βCode is available at: https://github.com/UNITES-Lab/GoA.β
βI want a repo that is in sync all the time with discussions that are happening out of band that I am not in. Think about even that concept. I like that thing because it sort of is sort of not possibleβ¦β
βCode is available at https://github.com/RL-MIND/OrthoReg.β
βWe release PaperMentor as open source for public use.β
βresend](https://github.com/resendlabs/resend-ruby) gem >= 1.0β
βa challenging real-world surveillance datasetβ
βThe generated images and source code are publicly available at https://github.com/viniciusorru/vcr-syntheticβ
βAccess to the code repository and dataset for this work can be found at https://csiro-robotics.github.io/WildCross.β
βCode, data, and models are available at intuitive-robots.github.io/sparc-labelingβ
βWe further introduce Interaction-Aware Bench (IA-Bench), a benchmark that measures model accuracy in grounding the locations of interacted objects in robot demonstrations.β
βOur code is available at https://github.com/Antonio-Dee/IIE_from_LLM.β
βCode is available at \href{https://github.com/Aalto-QuML/Hourglass}{this https URL}.β
βpeople are sleeping on how excellent goose has become under the hood (interface needs some work but team is pushing). it's a superpower.β
βCode and Dataset: https://github.com/smarizvi110/sentinel-benchβ
βCode is available on GitHub: https://github.com/ReinerBRO/HeLa-Memβ
βCode is available at: https://github.com/april-tools/delta-vi.β
βqmd-query-expansion-1.7B-q4_k_m | Query expansion (fine-tuned)β
βCodes are released at https://github.com/Yuzhe-Fu/FlashFPS.β
βTo support reproducibility and future work, we additionally release PLUM (Politeness Levels in Utterances, Multilingual), a publicly available corpus of 1,500 human-validated prompts across three langβ¦β
βOur code is available at https://github.com/happywinder/SCHK-HTC.β
βWe present TNRKit.jl, an open-source Julia package for Tensor Network Renormalization (TNR) of two- and three-dimensional classical statistical models and Euclidean lattice field theories.β
βBuilt on top of TensorKit.jl\cite{tensorkit}, it provides a symmetry-aware framework for constructing tensor-network representations of partition functions and coarse-graining them using methods such β¦β
βThe code is available at https://github.com/huidong-ma/FADE.β
βThe dataset and prompts are available at https://github.com/Hapluckyy/EVGeoQA/.β
βCode of the work is available at: https://github.com/palindromeRice/ClickBait_Detection_Architectureβ
βCode available at https://github.com/ryliu68/CAAP.β
βCorrespondingly, we contribute a benchmark of 26K samples (UI Comprehension-Bench) to comprehensively evaluate existing methods' mastery of UI elements.β
βConceptTracer is available at https://github.com/ml-lab-htw/concept-tracer.β
βOur code and datasets are available at \href{https://github.com/xbdxwyh/ChunQiuTR}{\texttt{github.com/xbdxwyh/ChunQiuTR}}.β
βCode is available at https://github.com/qipengz/BLAE.β
βTo ensure reproducibility, the full Python code is publicly available.β
βAll the code and experiments are publicly available at github.com/tiagobrogueira/Causal-Discovery-In-Exchangeable-Data.β
βAccelerating Deep Learning Research with the Tensor2Tensor Libraryβ
βOur code is available at https://github.com/OnnoNiemann/fp_diffusion_analysis.β
βWe publicly release JFinTEB datasets and evaluation framework at https://github.com/retarfi/JFinTEB to facilitate future research and provide a standardized evaluation protocol for the Japanese financβ¦β
βIt is publicly available at https://github.com/munich-quantum-toolkit/core.β
βProject page: http://compvis.github.io/myriad.β
βOur code is publicly available at https://github.com/gezbww/Vis_Prompt.β
βCode available at: https://github.com/NazirNayal8/MixFlowβ
βWe release all code, prompts, and cached results.β
βSource code is available at https://github.com/ProjectNeura/SegWithU.β