Leaderboard · HF 论文

AI 论文热榜

HF Daily · upvotes · 共 100 篇论文 · 11 月 18 日更新

HuggingFace 每日最热 AI 论文,按社区 upvotes 排,快速跟上前沿研究。

01 Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes Streaming audio-visual target speaker extraction (AVTSE) is essential for latency-sensitive applications. However, current causal systems face two coupled gaps. First, standard benchmarks fix the numb… △150热度
# 名称 热度
2 TeleChat to Xing4: Advancing Frontier Agentic Models on Domestic Chips and Frameworks We present Xing 4, a series of large language models that extends the TeleChat lineage through coordinated advances in model architecture and training infrastructure on Ascend. This report describes t… △149
3 SO-Arena: Benchmarking the Capability Spectrum and Reliability of System One Models System One models promise fast, general-purpose decision-making without lengthy token generation. However, understanding their capability spectrum and decision reliability requires more than aggregate… △137
4 Turns Matter: Advancing Streaming Video RL via Turn-Level Credit Streaming video understanding requires models to repeatedly decide whether to respond or continue observing. Recently, Group Relative Policy Optimization (GRPO) has been applied to this setting, with … △126
5 From Autonomous Agents to Cognitive Symbionts: Toward AI-Augmented Human Intelligence For a decade, progress in artificial intelligence has been measured by how much a machine can do on its own. Large foundation models now write code and run multistep tasks, and personal agents act on … △116
6 VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding Models for physical AI tasks, such as robotics and autonomous driving, need not reason solely in language. They can use visual plans--points, bounding boxes, and trajectories--to represent spatial goa… △106
7 Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs Diffusion vision-language models (DVLMs) process their entire input at every denoising step. Since visual tokens make up 89-97% of this input on the benchmarks we study, most of the decoding computati… △101
8 Advances in Agentic Computer Graphics Computer graphics is built on code. Large language model (LLM) agents can now generate graphics code and iteratively refine it through various feedback. This capability opens the door to a potentially… △100
9 SLA: Scaling Spatial-Language-Action Model via Continual Pre-training Reliable robotic manipulation requires both semantic understanding and precise control in three-dimensional space. However, vision-language-action (VLA) foundations largely inherit visual representati… △92
10 Learning Heterogeneous Tactile Representation for General Dexterous Manipulation Tactile sensing is an indispensable modality for contact-rich dexterous manipulation, a capability that hints at the ultimate frontiers of embodied intelligence. However, commercially available tactil… △92
11 CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements Despite recent advances in CUAs, their development remains constrained by the limited diversity, controllability, and reliability of interaction data. Moreover, conventional optimization pipelines lac… △91
12 AscendGYM: A Cost-Aware Kernel Optimization Benchmark for Real-World Workloads on Ascend NPUs Kernel optimization is essential for efficient large language model (LLM) training and inference on Ascend NPUs. Existing Ascend kernel benchmarks primarily focus on kernel generation, with less empha… △91
13 Wave Forcing: Towards Speed-of-Light Streaming Video Generation Real-time long-video generation requires continuous output with consistent appearance and natural motion. Existing chunk-wise autoregressive methods face challenges in both generation efficiency and l… △89
14 Envisioning Agentic Robotics: A New Era of Robotic Systems The release of GPT-6 Astra marks the emergence of a new paradigm in robotics: agentic robotics. Within weeks, frontier models with agentic harnesses matched or exceeded task-specific policies on many … △88
15 CoworkOS:Scaling Agent Coworkers for Real-world Automation Rapid advances in cowork agents are shifting human-AI collaboration toward real-world automation, delivering software, designs, and other artifacts. However, such productivity work demands both high-q… △87
16 Route Anything: A Study of Model and Policy Routing for General-Purpose AI Systems Artificial general intelligence (AGI) requires a method that can understand, generate, reason, and act across diverse domains and modalities. Rather than relying on a single model to master every capa… △87
17 Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agent We introduce Gamer, a generalist agent framework built for long-horizon tasks in complex interactive environments. Its end-to-end architecture combines perception, memory management, and multi-step re… △87
18 VibePrevisBench: Evaluating Agentic Coding for 4D Scene Generation in Blender Controllable real-world video generation models can condition on a rendered graybox proxy video, which fixes layout, motion and camera. Coding agents can build such videos by reconstructing a 4D scene… △86
19 Sage S2.1 Flash Technical Report We introduce Sage S1.5 Flash, a 320-billion-parameter general-purpose mixture-of-experts model designed to reason over scientific evidence and act in interactive environments. Sage Sci-Perception uses… △85
20 Decoupled Predictive Decision Making: A Shared Conditional Predictor for Agents Agent decisions depend on empirical relationships that deployment observations reveal and task descriptions alone may leave unresolved. We introduce Decoupled Predictive Decision Making (DPDM), an arc… △81
21 Tree-Ising: Repairing Language Models with Bit-Level Ising Edits Weight-space programming, introduced in recent MIT work by Takehi et al., enables a frontier LLM agent to read a network's weights and write a repair. Their GPT-6 Astra agent corrected the reasoning l… △77
22 A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement Recursive self-improvement requires models not only to acquire useful training experience, but also to decide when their current experience has ceased to be useful. Existing methods often focus on wha… △71
23 Proving and Improving the Platonic Representation Hypothesis with JEPAs Whether models trained on different modalities converge to the same representation of the world is central to AI. The Platonic Representation Hypothesis (PRH) conjectures that they do as they scale, b… △66
24 Harness-S: Learning from Sibling Harnesses for Generalizable Agent Training Harness evolution from a common base exhibits Locality, Complementarity, and Nonstationarity: variants repair different failures, and their utility changes as the policy learns. Rather than seeking a … △66
25 R^2Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization Loop In recent years, agentic orchestration has been widely applied to solve complex human tasks. However, existing orchestration learning still faces key challenges, including hand-designed curricula, adv… △65
26 Think Less, Locally: Local Preference Learning for Reasoning Compression Large reasoning models achieve strong performance on challenging tasks, but their long chain-of-thought often incurs substantial inference costs by continuing to deliberate after sufficient informatio… △65
27 SplatAnything: Gaussian Spacing Normalization for Feed-forward 3DGS across Arbitrary Scenes We 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 th… △64
28 InclusionMed: Benchmarking AI for Inclusive Healthcare Advancing medical AI for inclusive healthcare requires evaluation across diverse healthcare roles, tasks, and care settings, but benchmark coverage remains uneven. We introduce InclusionMed, an open m… △62
29 Video Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self-Improvement Video generation is shifting from end-to-end synthesis toward agentic generation, where planning, tool use, and feedback enable coherent, controllable multi-shot videos. In parallel, video world model… △61
30 Words Caught in the Heart: Simulating Person-Specific Expression for Self-Opaque Clients in Psychotherapy Psychotherapy clients may experience distress before they can coherently describe it, and their expression changes with emotion, perceived safety, and trust. Large language model-based client simulato… △61
31 AllocFlow: End-to-End Portfolio Trading Action Generation from Raw Market Data Real-world portfolio management requires converting noisy market observations into coordinated, simultaneous allocations across multiple assets under shared capital constraints. Advances in forecastin… △60
32 Don't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents External memory enables LLM agents to improve from experience by distilling trajectories of past tasks into concise lessons for new tasks. However, memory can also lead to memory-induced degradation, … △59
33 Does Scaling Toward AGI Depend on What System-1 Lets System-2 Execute? Progress toward artificial general intelligence (AGI) has largely relied on scaling a resource-intensive executive, System-2, through larger models, more data and compute, longer reasoning, and more a… △56
34 From Pixels to Actions - Towards Native Vision-Language-Action Policies Vision-language-action models are typically built on a simple premise: perception is first compressed by visual encoders, and action reasoning begins only afterwards. Yet manipulation often hinges on … △55
35 K2-Horizon: A Frontier Fleet of Open Source Language Models We present K2-Horizon, a fleet of six fully open language models, from a 0.9B dense model to a 375B-A23B MoE, built for general-purpose reasoning and agentic work across math and science, software eng… △55
36 Sage-Taiyi: A Metacognitive Architecture for Scientific Discovery We introduce Sage-Taiyi, a metacognition-inspired architecture that uses accumulated scientific understanding to guide what to investigate next and how to investigate it. Through explicit monitoring a… △51
37 Random Is Almost Enough? Stable and Low-Cost Benchmark Compression via BestRand Benchmark compression reduces the often prohibitive time and cost of model evaluation by evaluating models on a small benchmark subset that closely matches full-benchmark results. To quantify estimati… △50
38 World In-Context Learning for Agentic Robot Manipulation Trained action policies write manipulation skill into network weights, tying what is learned to the distribution it is learned from. In-context learning (ICL) avoids this coupling but has not matched … △50
39 DreamX: Video Diffusion Model is a Universal Latent Action Learner Learning a universal action representation from video requires modeling dynamics that are consistent across different executions of the same action yet invariant to changes in embodiment and appearanc… △49
40 WorldFoundry: Towards Unified Infrastructure for World Intelligence Visual generative models increasingly blur the line between synthesizing observations and simulating environments. Yet visual plausibility alone does not constitute successful world modeling: compelli… △48
41 OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images Generating videos of a specific subject from a few reference images remains challenging when the camera reveals surfaces that are not visible in the input. Early subject-to-video (S2V) methods conditi… △47
42 Toward the Era of Agentic Embodied Intelligence Foundation 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… △47
43 MIRIX-2.0: Multi-Agent Memory System Long-term memory lets LLM agents personalize, stay consistent, and reuse what worked before. Parametric memories need training, consolidation can lose details for good, and keeping every record leaves… △47
44 P^2-MOPD: Accelerating Multi-Teacher On-Policy Distillation via Parameter Priors Multi-teacher on-policy distillation consolidates expert capabilities by supervising student-generated trajectories, whereas task arithmetic offers a training-free alternative through linear parameter… △46
45 PhysLoop: Harnessing LLMs' Physics Awareness for Self-Improving Video Generation Models Video generation models produce visually realistic videos but still struggle with physical dynamics and causal consistency. Learning from generated videos requires fine-grained physical supervision, y… △46
46 BirdDreams: Joint Perspective and BEV Video Generation for a Plausible, Reactive Driving World Model Driving world models aim to simulate how a scene unfolds under different ego actions. This requires plausible motion of surrounding vehicles as well as precise ego-trajectory control. Learning vehicle… △45
47 Factorized MLLM Embeddings for Composed Image Retrieval Composed Image Retrieval (CIR) aims to retrieve a target image given a reference image and a modification text. Although recent approaches leveraging Multimodal Large Language Models (MLLMs) have show… △44
48 WeLM-Image: A Unified Image Generation Model towards Visual Intelligence We present WeLM-Image, a unified image foundation model that integrates multimodal understanding into text-to-image generation, instruction-guided editing, and multi-reference synthesis. Designed for … △44
49 SWE-CoWork: Benchmarking Coding Agents as Digital Employees in Organizations A coding agent working within a software organization must establish what to build, collaborate with colleagues, and verify what it delivers. We introduce SWE-CoWork, a benchmark comprising 101 develo… △44
50 REA: A Routed Embodied Agent Runtime for Asynchronous Brain-Cerebellum Control Foundation models are becoming remarkably reliable at high-level reasoning, yet they remain too slow and costly to serve as fine-grained controllers. Conversely, fast policies like VLAs and whole-body… △43
51 FrontierPhysics: Evaluating Agents for End-to-End Physics Research AI agents are playing an increasingly important role in physics research. However, existing physics benchmarks only evaluate fixed questions, isolated sub-tasks, or paper reproduction with given solut… △43
52 Scaling Mathematical Proof Supervision from Structured Textbooks Mathematical supervision for language models is typically flattened into isolated problem-solution pairs, discarding the curricular organization and evidential structure of the original sources. We in… △42
53 TailSteer: Trajectory-Tail Steering for Drift-Resistant Multi-turn Image Editing Strong single-turn editing performance does not guarantee reliable multi-turn interaction: as edited outputs are repeatedly reused, small unintended changes can accumulate into severe visual drift. Th… △41
54 ScaleVLA: Scaling Vision-Language-Action Models to 552 Billion Parameters Frontier Vision-Language Models (VLMs) such as GPT-6 Astra have demonstrated remarkable capabilities in robot control, suggesting that broad pretraining provides knowledge valuable for physical action… △41
55 SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt Injection Tool-using agents act on email, files, and payments, so an instruction hidden in a web page or a shared document can make an agent send data or money to an attacker. Many runtime defenses put a langua… △41
56 L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory Interactive world models generate visual content conditioned on user actions, yet maintaining spatial consistency over long-horizon exploration in real time remains challenging. Existing approaches re… △40
57 One Table, Many Queries: Benchmarking Generalist Tabular Models Across Generation, Imputation, and Prediction Generation, imputation, and prediction query different aspects of the same tabular distribution, but are usually evaluated separately. This leaves unclear which capabilities they share, how their trai… △40
58 G-STAR: Group-Scaled Token Capacity for Deeply Compressed Autoregressive Generation Discrete autoregressive models offer a scalable framework for image generation. However, they face a fundamental trade-off: long token sequences preserve representation quality but slow generation, wh… △40
59 Weight-Space Programming Doesn't Need Transformers Standard neural architectures such as the Transformer were chosen because they train well with gradient descent and run fast on GPUs. In weight-space programming, a large language model (LLM) writes t… △39
60 Democratizing Robot-Use Agents: A Unified Harness with Open Models Robot-use Agents (RUAs) have shown promising zero-shot manipulation capabilities, but reliance on frontier, proprietary models limits research into further training. To democratize RUA research, we in… △38
61 Axion 1.0: Open Agent Foundation Models, Simplified We introduce Axion 1.0, a fully open agent foundation model that combines strong and broad agentic capabilities with a remarkably simple training recipe. Axion 1.0 is trained in only three stages: two… △38
62 Halley: A Predictive Control Plane for Optical AI Data Center Networks A frontier AI model is trained in an AI data center, on tens of thousands of accelerators joined by a dedicated network, and every training step ends with all of them exchanging data at once. Between … △38
63 PCBRouteAgent: 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 nat… △37
64 Reframe: Observation-Aligned Multi-Teacher On-Policy Distillation for Agentic Visual Reasoning Agentic 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. M… △37
65 Open Vision Banana: A Fully Open Recipe for Generative Visual Perception Recent work suggests that pretrained image generators encode real-world understanding beyond image synthesis. Vision Banana exploits this by framing vision tasks as conditional image editing. However,… △37
66 ForceHarness: Turning Force into Action and Physics for Frozen Frontier Models Frontier multimodal models can now control robots zero-shot from images, yet many manipulation tasks depend on contact forces that images cannot show. Bringing force to an API-only frozen model raises… △37
67 What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents? While multi-turn agentic reinforcement learning (RL) excels on long-horizon tasks, its performance gains remain highly sensitive to interaction constraints. Evaluating across sampling breadth K and in… △35
68 Few-Step Streaming Video Generation via Condition Shifting Few-step sampling reduces the cost of streaming video generation. Distribution Matching Distillation (DMD) supervises few-step generators with a separate fake-score network, which adds training memory… △35
69 Duo: A Reciprocal World Model for Full-Duplex Interaction In this report, we introduce the Reciprocal World Model (RWM) and present Duo v1, a full-duplex world model that continuously perceives audiovisual inputs while responding to users in real time. The R… △35
70 MMFlash: Faster Speculative Decoding for Vision-Language Models Speculative decoding accelerates generation by letting a lightweight drafter propose tokens for parallel verification by a target model. Diffusion drafters such as DFlash propose an entire token block… △35
71 Apriel Voice 27B Preview: An Open Model for Speech, Reasoning, and Tool Use A capable voice assistant must do more than recognize words; it must understand requests, reason over context, sustain conversations, and act through tools. We present Apriel Voice 27B Preview, an ope… △34
72 SWE-Trail: History-Guided Trajectory Collection for Coding Agent Training Coding agents solve repository issues through long sequences of exploration, editing, and validation. These trajectories are increasingly used as post-training data, so how they are collected shapes w… △34
73 IdeaTaste: Do LLMs Share the Research Taste of Human Researchers? Research taste, the judgment of what to read, which problems to pursue, and which methods to try, increasingly shapes the work of AI scientists, yet it remains far less understood than their ability t… △34
74 ToolSpace: Scaling Tool-Centric Environment Synthesis for Long-Horizon Agents Large language models are deployed as long-horizon agents that compose diverse tools across MCP services into executable workflows. Existing MCP environment-scaling methods are data-centric: they firs… △34
75 Actor, Judge, or Teacher? Understanding Decision Models in Long-Horizon Agents Decision models answer a question with a typed output, such as a choice among options with a probability for each, so one model can choose an agent's actions, evaluate actions already taken, or score … △34
76 EvoMemState: Evolving Memory State for Personal Agents Long-term memory enables large language model (LLM) agents to provide continuous personalized assistance by retaining user information across interactions. Existing systems support this process throug… △33
77 SteerDistill: Quantizing LLM Agents via Closed-Loop Teacher Steering Low-bit quantization reduces the inference cost of LLM agents but can compromise task success. Examining failed rollouts, we find that quantized agents overlook task requirements or environmental cond… △33
78 Multi-Branch Transformer Transformer language models are commonly scaled by making their blocks wider or stacking them deeper. In this work, we explore a complementary path: branching, the parallel composition of full Transfo… △33
79 Beyond Answering: Learning to Speak First and Act in Streaming Video Most AI assistants respond only when prompted, remaining silent even when events in the video stream offer meaningful opportunities for conversation. To move beyond purely user-driven interaction, we … △33
80 Open-HumanScale: An Open Recipe for Scaling Human and Robot Experience for Embodied Foundation Models Egocentric human video offers a scalable source of manipulation priors for robot learning, yet translating raw data scale into generalizable robot policies demands rigorous data curation and training … △32
81 dNaViT: Discrete Codes are General-Purpose Visual Representations Discrete autoregressive modeling, notably through next-token prediction, has become a cornerstone of modern language models. Extending this paradigm to vision allows visual and language models to conv… △32
82 LowRAM: Low-Rank Keys and Amortised Values for Composable KV Cache Compression at Test-Time Autoregressive 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 t… △30
83 Ropedia Xperience 2: A Gold Standard for Scaling Physical AI Environments and Behaviors Large foundation models such as GPT-6 Astra and Claude Fable 5.1 have recently been shown to control robots directly from visual observations. They nevertheless remain brittle on long-horizon, contact… △30
84 Breath-Dx: A Time Series Classification Benchmark for Disease Screening with eNose Electronic nose (eNose) technology offers a portable, non-invasive route for disease screening via exhaled breath analysis. However, progress in the field is hindered by the lack of systematic benchma… △30
85 A Broader Look into MLLM's Retrieval Heads Locating relevant evidence in long inputs is a core capability of Multimodal Large Language Models. Prior studies attribute this capability to retrieval heads, a sparse set of attention heads that tra… △29
86 Behind Video Generation: Observations and Insights on Multimodal Understanding from Kling Video generation has progressed from isolated clips to coherent short-form audiovisual sequences, and the bottleneck is shifting from rendering to semantic control. This report summarizes the observat… △29
87 LongBanana: An Expert-Verified Benchmark for Long-Context Multi-Reference Image Synthesis We 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… △29
88 Follow the Gradient: Tracing Safety Degradation Back to Training Data Fine-tuning Large Language Models (LLMs) on instruction data can quietly erode their safety, even when no training example looks harmful. Because this safety-degrading data looks benign, standard cont… △28
89 PhotoGuider: Composition-Aware Cropping and 360^{circ} View Framing with Explainable Photographic Assessments Traditional image cropping assumes the photograph already contains the composition worth keeping, and asks only where to crop. A full 360^{circ} scene offers no such guarantee: the viewing direction i… △28
90 Order-Only On-Policy Distillation On-policy distillation (OPD) trains a student on its own generations by matching the teacher's token probabilities. These probabilities entangle two kinds of information: which tokens the teacher pref… △28
91 Incentivizing Self-Learning in Large Language Models via Reinforcement Learning Large language models (LLMs) draw on parametric knowledge and retrieval-augmented generation (RAG) to solve knowledge-intensive tasks. Yet problem solving in unfamiliar domains calls for tightly coupl… △28
92 Self-Improvement Memory Enables Continual Recursive Self-Improvement Harness optimization is often studied with a fixed policy model and benchmark. When either changes, the optimizer must decide which parts of an evolved harness to reuse or revise, but the harness alon… △28
93 NorthCUA Technical Report: Turbocharging Computer-Use Agents through Experience at Scale Scaling computer-use agents from individual actions to complex software work requires experience that connects decisions to complete outcomes. We present NorthCUA, an integrated system for turbochargi… △27
94 Lost in Recovery: Demystifying Recovery Behavior of Computer-Use Agents via Goal-Oriented Action Replay Recent advances in large (vision) language models have enabled computer-use agents that automate digital workflows via fine-grained keyboard and mouse operations. However, such agents remain fragile i… △27
95 LLMs Don't Know What They Know: Benchmarking Temporal Self-Knowledge for Financial Backtesting Financial 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 s… △27
96 The Last Mile to the Real World: Agent-Native Primitives as Reusable Building Blocks for Solving Real-World Tasks How can an agent handle a real-world task end to end? Frontier models with their own harnesses still fall short on real-world benchmarks: on Terminal-Bench 4.0, GPT-5.6 Sol with Codex resolves 37.3% o… △27
97 Embodied First Exam Early successes on agentic robotics point to a potential paradigm shift toward using coding agents to control robots. Existing robotics benchmarks are built around visuomotor policy learning, leaving … △27
98 WeFair: Fidelity-Aware Alignment from Human Feedback for Personalized Query Rewriting in Short-Video Search Short-video search needs compact query rewriters that recover users' personalized intent from ambiguous queries under strict latency constraints. Existing LLM-based methods have improved rewriting by … △26
99 YANAMI: A Large-Scale Multimodal Dataset and Benchmark for Multiturn Stateful Interaction Unified Multimodal Models (UMMs) integrate visual understanding, generation, and editing within a single unified framework. However, existing unified multimodal datasets and benchmarks remain dominate… △26
100 Flide: Accelerating Decision Inference with Exact State Forking Decision 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, existin… △26