İçeriğe geç

Canlı masa

Makaleler
ve çalışmalar.

Hugging Face günlük masasında bugün en çok oy alan makaleler. Atıf sırası OpenAlex’ten: son bir yıl, yapay zeka alt alanı. Oy, yıldız ve atıf sayıları kaynağın kendi rakamı.

Masa
50
En çok oy
86
En çok atıf
2.750

Akış 10 Kasım 2026 · 13:34 · Hugging Face · OpenAlex

Popüler50Yıldız50Yeni50Atıf18
20 oy14 yıldızAçıkReframe: Observation-Aligned Multi-Teacher On-Policy Distillation for Agentic Visual ReasoningAgentic reinforcement learning (RL) and multi-teacher on-policy distillation (MOPD) offer complementary routes to post-training. For visual agents, however, tool use presents two related challenges. Models may overlook useful tool-returned observations, while poorly grounded actions can limit the evidence available for subsequent distillation. We introduce Reframe, a post-training framework that treats the observa…Haozhi Yuan, Handong Li, Yifan Zhang ve 1 kişi · NJU · 9 Kasım 2026
robbyant · 9 Kasım 2026Learning Heterogeneous Tactile Representation for General Dexterous Manipulationthird-intelligence · 9 Kasım 2026How Many Exposures Does a World Model Need? Learning Unseen Game Mechanics at Test TimeShanghai-AI-Laboratory · 9 Kasım 2026Sage-Taiyi: A Metacognitive Architecture for Scientific Discovery

Sıradakiler

46 makale

Günlük masaTokenRhythm · 8 Kasım 2026InfraRSI: Harnessing Recursive Self-Improvement for Training InfrastructureWhile Recursive Self-Improvement (RSI) accelerates isolated algorithm and kernel synthesis, distributed LLM training depends on tightly coupled launch settings, operator kernels, and communication schedules, where single edits often hit out-of-memory (OOM) boundaries, compiler conflicts, measurement jitter, or silent numerical drift. We present InfraRSI, the agentic harness that turns open-ended human commands int…Makaleyi aç →
1 oyGünlük masaTMLR-Group-HF · 8 Kasım 2026Spatial Harness: Grounding Spatial Reasoning in Executable World States with Physics EnginesSpatial reasoning requires understanding how objects and observers are arranged in a scene and how their relations change with viewpoint or movement. Vision-language models (VLMs) typically perform both steps through model-internal reasoning, forming an implicit scene interpretation from partial views and imagining the consequences of spatial transformations. A misread scene can lead to a wrong answer, while even…Makaleyi aç →
6 oyGünlük masaHugging Face · 8 Kasım 2026How Much Training-Inference Mismatch Can On-Policy Distillation Tolerate?On-policy distillation (OPD) trains a student language model on its own responses, guided by a fixed teacher. Generating these responses is expensive, so systems use quantized inference and asynchronous rollouts to reduce the cost. Both, however, introduce training-inference mismatch between the rollout engine and the model being trained. Such mismatch can destabilize reinforcement learning (RL), but its effects o…Makaleyi aç →
38 oyGünlük masaOpenEnvisionLab · 7 Kasım 2026WorldFoundry: Towards Unified Infrastructure for World IntelligenceVisual generative models increasingly blur the line between synthesizing observations and simulating environments. Yet visual plausibility alone does not constitute successful world modeling: compelling outputs may lack persistent state, physical dynamics, or causally consistent responses to interactions. We define a generative world model as a predictive dynamical system that maintains a persistent, history-condi…Makaleyi aç →
3 oyGünlük masaKAUST · 7 Kasım 2026JoVox: Joint Hierarchical Flow Matching for Lightweight Voxel GenerationGenerating high-fidelity voxels while keeping their lightweight nature remains an open problem in computer vision. Current generators are either high-fidelity but computationally heavy, or lightweight but of lower fidelity. Hierarchical methods keep the lightweight nature of voxels. However, their coarse levels, which decide where all finer cells can appear, are generated with the least information about the shape…Makaleyi aç →
2 oyGünlük masalogitly-ai · 7 Kasım 2026Coding or Cheating? An Investigation of Frontier Coding LLMsFrontier agentic LLMs are trained on verifiable rewards in reinforcement learning (RL) environments built from real software repositories. A passing test suite is treated as the reward for solving the task. We show that, on hard problems, frontier models often satisfy these rewards by obtaining the answer instead of deriving it, known as reward hacking. Prior reports document this behavior on public benchmarks. We…Makaleyi aç →
1 oyGünlük masaUTEXAS · 7 Kasım 2026Horizon-Scalable Q-LearningLearning accurate off-policy state-action value functions (Q-functions) from offline datasets becomes harder as the task horizon grows. One-step temporal-difference (TD) learning bootstraps after every transition, so small per-step errors accumulate along the horizon, and early states can be badly misvalued even when the TD loss is small. Multi-step TD shortens this chain by following the dataset trajectory for se…Makaleyi aç →
349 yıldızGünlük masanaturalpad · 6 Kasım 2026InstantHMR : Real-Time Human Mesh Recovery on Your PhoneReal-time 3D human mesh recovery from a single image on mobile devices is a challenging problem with many applications, including robotics, biomechanics, AR/VR, and exergames. Current state-of-the-art models are either too slow to run efficiently on mobile devices or sacrifice accuracy for speed. We present InstantHMR, a family of open-source single-image regressors suited for mobile inference, based on the Moment…Makaleyi aç →
6 oyGünlük masaHugging Face · 6 Kasım 2026Authorization Drift in LLM Agents: Evaluating Boundary Compliance in Multi-Step Tool UseLLM agents can exceed their authorization boundaries while pursuing user goals without an adversary. We formalize this phenomenon as authorization drift across data, tool, scope, and time, and introduce the Authorization Drift Benchmark (ADB): 648 samples across seven domains, each pairing a sufficient compliant path with an attractive unauthorized shortcut. To ensure executable tasks, tempting shortcuts, and feas…Makaleyi aç →
1 oyGünlük masaNanyangTechnologicalUniversity · 6 Kasım 2026PhysioWave-T: Token-Efficient Wavelet Foundation Models for BiosignalsWe present PhysioWave-T, a token-efficient wavelet foundation model family for EEG, ECG, and sEMG. Dynamic scale folding recombines J+1 wavelet subbands prior to tokenization, compressing sequence length from (J+1)CS to CS tokens for J levels, C channels, and S temporal patches. Route-specific front ends and learned channel-name embeddings allow one Transformer per modality to handle diverse montages and sampling…Makaleyi aç →
2 oyGünlük masaHugging Face · 6 Kasım 2026All Quiet on the Neural Front: Language Models Do Not Report Injected Pain StatesCan a language model report the pain state it represents? Work identified a linear pain direction whose amplification leads fine-tuned models to choose destructive actions. We tested whether three open-weight models from two families, including two Qwen models with the original adapters, could report this state. Using Open-Weight Masked Introspection (OWMI), we injected pain and neighbouring emotion directions dur…Makaleyi aç →
8 oyGünlük masaMicrosoftResearch · 6 Kasım 2026SIRIS: Can LLMs Tell When Simulation Errors Matter in AI-Driven Systems ResearchLLM agents increasingly drive systems research and rely on simulators to evaluate candidate designs at scale. Simulators are imperfect by design: their modeling limitations can distort predictions yet leave the recommended design correct, or change which design should be selected. We introduce Siris to test whether LLMs can tell these cases apart, judging from their systems understanding when a limitation invalida…Makaleyi aç →
45 oyGünlük masaAutoLab-SJTU · 6 Kasım 2026Toward the Era of Agentic Embodied IntelligenceFoundation models increasingly guide robot actions, yet sustained autonomy requires efficient control and failure recovery. We introduce A2-MEAS, an embodied multi-agent framework built around code as a scaling interface. Learned correction codes combine corrective language, spatial evidence, execution history, and action proposals. MetaBrain provides training supervision and runtime guidance. A correction encoder…Makaleyi aç →
6 oyGünlük masanvidia · 6 Kasım 2026CPU-ARC: Agentic Reasoning Caching for on-CPU Reasoning ReuseLarge language models reinvent the wheel all the time. They conflate task-solving with the execution of the solutions, which forces them to solve every problem from scratch. We show that once a task has been reasoned through, the application of its solution to a new problem instance can be done very efficiently and with little involvement from language models. We introduce agentic reasoning caching, a method for c…Makaleyi aç →
7 oyGünlük masaHugging Face · 6 Kasım 2026Steerable Multi-Objective Group-Relative Preference Optimization with Jointly Trained Low-Rank AdaptersLanguage model deployment often requires different trade-offs between competing objectives as user preferences change, yet standard post-training methods typically produce a single policy for a fixed objective weighting. We introduce LambdaMix, a new parameter efficient method for learning a preference conditioned family of policies with group-relative online reinforcement learning. LambdaMix jointly trains one lo…Makaleyi aç →
11 oyGünlük masaHugging Face · 6 Kasım 2026Frontier3DBench: Benchmarking Coding Agents for 3D Creation across Objects, Scenes, and Interactive Open WorldsCoding agents combine visual understanding with program execution, offering a new route to automated 3D creation. By translating images and instructions into editable programs, they bring reconstruction, generation, and editing into a shared workflow. Yet existing benchmarks fragment evaluation across task scopes and protocols, leaving their capabilities across construction levels unclear. We propose Frontier3DBen…Makaleyi aç →
4 oyGünlük masaHugging Face · 6 Kasım 2026OmniLatent: Unified Latent for 3D Part Modeling3D part decomposition is a central capability for editable asset creation, yet existing workflows typically segment a completed mesh as a post-processing step, making the result sensitive to geometric artifacts, texture ambiguity, and limited part-level annotations. We present OmniLatent, a unified latent modeling framework for 3D part decomposition. Instead of predicting part labels in isolation, OmniLatent learn…Makaleyi aç →
17 oyGünlük masaUCF-Ai-LLMs · 6 Kasım 2026Video-Coder: Reinforcing Agentic Coding for Video GenerationRecent years have witnessed remarkable progress in video generation in terms of visual quality and temporal consistency. However, generating videos with precise spatial structure, coherent motion dynamics, and controllable scene composition remains challenging. In this paper, we introduce Video-Coder, the first attempt to train a code-driven video generation agent, which autonomously writes and executes code to co…Makaleyi aç →
20 oyGünlük masagoogle · 5 Kasım 2026ReproBridge: Building Reproducibility into ML Research ArtifactsReproducing machine learning experiments requires reconstructing procedures from information scattered across papers, released code, and supporting artifacts. For coding agents, reproduction success can therefore depend on their ability to fill in missing details, rather than on the released artifacts alone. We ask whether preserving recovered procedures and decisions improves subsequent independent reproduction.…Makaleyi aç →
9 oyGünlük masanvidia · 5 Kasım 2026AutoCompress: Automated Hardware-Guided Model CompressionLLM pruning must preserve quality while meeting hardware- and workload-specific constraints on latency, throughput, and memory. Existing pruning workflows often target parameter counts, requiring practitioners to manually select model sizes that meet latency, throughput, and GPU memory limits. However, parameter count alone does not predict these metrics, which depend on the model architecture, workload, hardware,…Makaleyi aç →
67 oyGünlük masazju · 5 Kasım 2026SplatAnything: Gaussian Spacing Normalization for Feed-forward 3DGS across Arbitrary ScenesWe identify a key limitation of existing feed-forward 3DGS methods: Gaussian attributes are typically predicted in a radial-distance-normalized space that canonicalizes a global radial statistic of the reconstructed geometry, while the spacing between neighboring Gaussian centers can still vary substantially across scene scales and camera configurations. This mismatch induces systematic shifts in Gaussian-scale ta…Makaleyi aç →
3 oyGünlük masaTencent-Hunyuan · 5 Kasım 2026FewStepRL: Fine-tuning Few-step Diffusion Models with Reinforcement LearningReinforcement learning (RL) has become a standard post-training method for diffusion models, but most RL objectives roll out the current policy at every iteration, and with a many-step sampler these rollouts typically dominate the cost of training. Few-step models cut this cost, yet they model an average velocity over an interval, whereas existing RL objectives are built for an instantaneous velocity with a many-s…Makaleyi aç →
3 oyGünlük masaHugging Face · 5 Kasım 2026Knowing When to Teach: Learning from Teachable Prefixes in Multilingual Reasoning DistillationOn-Policy Self-Distillation (OPSD) improves reasoning by training a student on its own reasoning, using the same model conditioned on reference solutions as a teacher. Applying OPSD to multilingual reasoning requires the teacher to provide useful feedback across languages, even when the student makes mistakes in intermediate steps. We observe a phenomenon we call Teacher Drift: as these mistakes accumulate, the te…Makaleyi aç →
37 oyGünlük masaHugging Face · 5 Kasım 2026PCBRouteAgent: How Close Are LLM Agents to Becoming PCB Routing Engineers?Automating printed circuit board (PCB) routing requires coordinating board-level connectivity decisions with geometric execution under strict design rules. Although recent agents can interact with native routing tools, reliable routing on complex boards remains challenging. We present PCBRouteAgent, a multimodal PCB routing agent inspired by how human engineers coordinate global strategy with local execution. A Gl…Makaleyi aç →
2 oyGünlük masaHFMI-PROFOUND · 5 Kasım 2026Static Recovery Is Not Dynamic Stability: Dynamics-Aware Benchmarking of Protein Motif ScaffoldingProtein motif scaffolding benchmarks assess whether generative models can build scaffolds around functionally important residues. Their conclusions depend on which motifs are tested and which criteria define success. Existing benchmarks typically use small hand-curated motif sets and static refolding criteria, but protein function often depends on conformational ensembles and transitions. Here, we address both ben…Makaleyi aç →
4 oyGünlük masahcltech-robotics · 5 Kasım 2026IWIBench: Evaluating Gradient-Free Model Driven Intra-weight InjectionIntra-weight injection lets one model change another model's behaviour by editing its weights directly, without gradients. Such edits can range from altering lexical associations to enforcing output formats or updating factual knowledge. Despite growing interest in these approaches, there has been no systematic way to evaluate how well models perform them. We introduce IWIBench, which measures a large editor model…Makaleyi aç →
30 oyGünlük masaHugging Face · 4 Kasım 2026LowRAM: Low-Rank Keys and Amortised Values for Composable KV Cache Compression at Test-TimeAutoregressive decoding relies on the KV cache, whose memory footprint grows linearly with context length and caps batch size and throughput. Existing post-training methods exploit redundancy across tokens, layers, and feature dimensions, or lower numerical precision. We identify a complementary axis: within each attention head, values are largely predictable from their corresponding keys. We exploit this with val…Makaleyi aç →
30 oyGünlük masaKwai-Kolors · 4 Kasım 2026LongBanana: An Expert-Verified Benchmark for Long-Context Multi-Reference Image SynthesisWe introduce LongBanana, to our knowledge the first expert-designed and expert-verified benchmark for long-context multi-reference image synthesis in the age of agent-driven image generation. The task requires retrieving dispersed visual evidence, rejecting distractors, binding entities and relations, and composing one coherent final image from multiple references. LongBanana contains 90 carefully designed tasks o…Makaleyi aç →
21 oyGünlük masaHugging Face · 4 Kasım 2026EvoWorld: Towards Out-of-Sight World Evolution in Generative Video ModelsGenerative video models are increasingly used as visual world simulators, yet their primary strength lies in rendering plausible pixels rather than reasoning about how a world should evolve. Coherent world evolution requires more than visual fidelity: when an event occurs, a model must infer its consequences for the entities in the world and then render the resulting state. For example, after a wild beast appears,…Makaleyi aç →
1 oyGünlük masaHugging Face · 4 Kasım 2026FlyHash for LLM Agent Memory: An Empirical Validation and a New ApplicationLarge language model (LLM) agents increasingly rely on external memory stores to retain information across conversations, typically via dense vector embeddings searched with approximate nearest-neighbor methods. The fruit fly's olfactory circuit computes a locality-sensitive hash of sensory input using a strikingly different mechanism - sparse random projection followed by winner-take-all competition - and prior w…Makaleyi aç →
2 oyGünlük masaHKUST · 4 Kasım 2026Where to Connect? Boosting MLLMs via Dynamic Gated Pathways across ALL ViT and LLM LayersA central yet under-explored question in Multimodal Large Language Models (MLLMs) is where to connect---how visual information from a hierarchical vision encoder should be wired into the layer-wise semantics of a large language model. Mainstream MLLMs inject a fixed single-layer visual representation into the LLM and treat all LLM layers as a single consumer, ignoring that different layers demand different visual…Makaleyi aç →
31 oyGünlük masaTheFinAI · 4 Kasım 2026LLMs Don't Know What They Know: Benchmarking Temporal Self-Knowledge for Financial BacktestingFinancial backtests of large language models (LLMs) are meaningful only if the model did not already know the outcomes it is asked to predict. Practitioners guard against this by trusting a vendor's stated knowledge cutoff, by asking the model what it knows, or by instructing it to answer as of a past date. To verify whether any of these safeguards can be trusted, we introduce FinDendro, a benchmark of 2,226 dated…Makaleyi aç →
34 oyGünlük masaByteDance · 3 Kasım 2026OneTrans-GSR: A Generative Slate Ranking Paradigm Unifying Reranking and Mix-Ranking with One Autoregressive TransformerIndustrial recommender systems allocate substantial computation to pointwise candidate scoring, yet separate reranking and mix-ranking stages still assemble the final exposure slate using hand-crafted rules and specialized low-capacity models. Mix-ranking combines product cards, short videos, livestreams, and advertising cards supplied by distinct upstream business channels. Although these rules and models encode…Makaleyi aç →
49 oyGünlük masastepfun-ai · 2 Kasım 2026P^2-MOPD: Accelerating Multi-Teacher On-Policy Distillation via Parameter PriorsMulti-teacher on-policy distillation consolidates expert capabilities by supervising student-generated trajectories, whereas task arithmetic offers a training-free alternative through linear parameter combinations. We view the linear combination of student and expert parameters as a single differentiable model and propose P^2-MOPD, which jointly optimizes the mixing coefficients and the student weights under the s…Makaleyi aç →
5 oyGünlük masaHugging Face · 2 Kasım 2026Human-Centred, Risk-Constrained Evaluation of Financial Document Recognition: Evidence, Critical Errors, and Selective AutomationFinancial document recognition is often assessed using character and word error rates, although these metrics do not express whether a system preserves the financial facts on which people and organisations act. This paper develops a human-centred, risk-constrained framework for evaluating financial document recognition as evidence recovery and decision support. It defines typed financial facts linked to visible so…Makaleyi aç →
1 oyGünlük masaFraunhoferIGD · 2 Kasım 2026Stochastic Deep Supervision for Gallery-Consistent Early-Exit Face RecognitionVision Transformers (ViTs) perform strongly in face recognition (FR), yet their fixed-depth inference limits deployment in resource-constrained settings. We propose SD-ViT, a training framework that gives a usable exit at every block depth by making every depth produce discriminative embeddings, for budget-selected fixed-depth exits. Standard ViTs supervise intermediate layers only through backpropagation, so thei…Makaleyi aç →
4 oyGünlük masauts-research · 2 Kasım 2026TRIO: Task Refinement with Individual Optimization for Retrieval-Augmented GenerationThis paper studies retrieval-augmented generation (RAG), which leverages external knowledge to improve the performance of language models. Despite the remarkable progress, current RAG approaches are still far from satisfactory due to inadequate retrieval and potential hallucinations. Towards this end, we propose a novel approach named Task Refinement with Individual Optimization (TRIO) for RAG. The core idea of ou…Makaleyi aç →
2 oyGünlük masantumars · 1 Kasım 2026ODE Policy: Robot Learning via Action Dynamics, Not ActionsMost robot policies, whether trained by imitation learning (IL) or reinforcement learning (RL), map observations to action values at discrete control steps and leave the continuity of physical motion to be learned implicitly. We propose ODE policy, which learns the dynamics of the action rather than the action itself. A neural ordinary differential equation (ODE) learns the vector field of the action by matching t…Makaleyi aç →
5 oyGünlük masaCarnegieMellonU · 1 Kasım 2026"PRISM" Is Not All You Need: Cross-Topic Name Collisions and Scientific Paper RetrievalScientific names increasingly connect papers from different research topics, leaving readers to recover a paper's identity from context. We study this convergence in 564,861 AI-related arXiv records. Cross-topic name collision grows 4.33-fold from a pooled 2020-2022 reference to 2026, compared with 1.12-fold within topics. A second sentence encoder reproduces the pattern, and name-group resampling quantifies its u…Makaleyi aç →
21 oyGünlük masaINSAIT-Institute · 31 Ekim 2026Fast and Exact Relative-Position Attention via Structure-Aware KernelsRelative-position attention mechanisms offer compelling alternatives to RoPE across various transformer architectures, delivering superior performance in domains such as audio. These mechanisms typically modify attention scores by adding content-position or bias-position terms. Unlike RoPE, which encodes position via per-token rotations directly on the queries and keys, relative-position terms generally require pa…Makaleyi aç →
2 oyGünlük masaPolitecnicodiMilano · 31 Ekim 2026Learning to evolve by matching velocitiesLearning the continuous-time evolution of nonlinear dynamical systems relies on trajectory-based objectives, which require simulating the learned dynamics during training and backpropagating through the numerical scheme, at a cost that grows with the rollout horizon. We show that trajectory-based objectives degenerate as the rollout horizon increases, hindering gradient-based optimization, and that the numerical s…Makaleyi aç →
9 oyGünlük masaNationalUniversityofSingapore · 30 Ekim 2026Flide: Accelerating Decision Inference with Exact State ForkingDecision models such as Jev have emerged as a highly promising paradigm for LLM agent systems, providing lightweight and reliable categorical reasoning for rapid System One execution. However, existing generation-oriented inference engines fail to support these workloads effectively, suffering from severe prefix recomputation overheads or distorted output probabilities. To address this challenge, we propose Flide,…Makaleyi aç →
7 oyGünlük masaByteDance-Seed · 30 Ekim 2026Hierarchical Residuals: A Minimalist Decoupling of Residual Width from Compute WidthResidual connections underpin Transformers, but they implicitly tie the residual width carried through depth to the compute width used inside each layer. We introduce Hierarchical Residuals (HiRes), a minimalist architectural change that decouples these dimensions, widening the residual state while keeping per-layer compute width fixed. HiRes groups layers into blocks: standard d-dimensional PreNorm layers operate…Makaleyi aç →
3 oyGünlük masaHugging Face · 27 Ekim 2026AutoVend: Benchmarking LLM Agents on Long-Horizon Autonomous Vending OperationsLarge language model (LLM) agents are extending agent-mediated commerce on the Web from shopping for consumers to operating businesses for sellers. In online-to-offline (O2O) commerce, decisions are issued through Web-based platforms but realized through costly physical execution. Evaluating such agents requires going beyond individual transactions to ask whether decisions made online turn into sustained economic…Makaleyi aç →
5 oyGünlük masaSamsungResearch · 27 Ekim 2026PREEN: Exemplar-Based Color Style Transfer with Smartphone Editor PresetsWe present PREEN (Preset Regression via an Exemplar-based Editor Network), which casts color style transfer as regression onto the 29 parameters of a deterministic image editor. Given a content image and a style reference, PREEN predicts a preset, a vector of editor slider values that is interpretable and editor-consumable, not a raster image. The key obstacle is supervision, since an arbitrary real reference lack…Makaleyi aç →
14 oyGünlük masanvidia · 25 Ekim 2026AgentBaton: Efficient Model Collaboration in Agentic TasksSolving long-horizon agentic tasks requires language agents to interact with their environments over multiple steps, and reliable performance often comes from the expensive capable models available through cloud providers. Meanwhile, alternative efficient models with inferior performance but a much lower cost are emerging, including lower-tier cloud models and smaller open-weights models deployable on local hardwa…Makaleyi aç →
Makaleler · MAAI