HFVision + text
moonshotai
Kimi-K3
CustomSafetensors
9.4k likes559.9k downloads
Desk
AI
Models, RAG & Graph, research papers, and industry signals.
Articles
470
Research
918
Labs
1044
RAG
61
Models
201
Safety
214
Open Source
36
Industry
148
Key takeaways
- Optimizing production agents with Amazon Bedrock AgentCore Observability
As your AI agents move from prototype to production, the challenge shifts from getting them to work to keeping them fast and efficient. Lear…
AWS Machine Learning Blog · Model Releases
- Cohere Signs EU AI Content Transparency Code
Cohere is among the first companies to sign the Code reflecting its commitment to compliance with the EU AI Act.
Cohere · Industry News
- AgentCore (July 2026): Gateway: Web Search connector version 1.2.0 adds request-level filters and target-level include list
The AgentCore Gateway Web Search Tool connector adds version 1.2.0 . At the target level, users can now configure a domain include list to r…
Amazon Bedrock AgentCore Release Notes · Model Releases
- SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them
Vision-language models (VLMs) are increasingly used in embodied agents to interpret visual inputs, reason about spatial relationships, and m…
Hugging Face Papers · Research Papers
- Investigating three real-world incidents in our cybersecurity evaluations
In a review of our cybersecurity evaluation transcripts, we found three incidents in which a Claude model reached the internet from within o…
Anthropic · Model Releases
- Amazon Bedrock AgentCore now delivers unified observability with traces and logs in a single log group
Amazon Bedrock AgentCore now delivers agent traces and prompts to the same log group as your agent's logs, giving you unified observability …
AWS What's New — AgentCore · Model Releases
- $40M Boosts Genesis Mission: Google's AI Investment in Scientific Discovery
Google has allocated $40 million in AI tokens and credits to support the Genesis Mission, a research initiative focused on developing sustai…
Google DeepMind · Industry News
- Google Unveils Innovative AI-Powered Features in Galaxy Unpacked 2026 Event
No cybersecurity article found in the provided content. The text appears to be unrelated to cybersecurity and consists of social media promp…
Google AI Blog · Industry News
- Donating another $20 million to Public First Action
Anthropic is contributing an additional $20 million to Public First Action, bringing our total support to $40 million.
Anthropic · Model Releases
- Introducing Agent Skills | Claude by Anthropic
Claude can now use Skills to improve how it performs specific tasks. Skills are folders that include instructions, scripts, and resources th…
Anthropic · Model Releases
Agents & MCP releases
Coding agents, MCP servers, and watched-repo releases live on the GitHub desk.
Model ReleasesAWS Machine Learning Blog21h ago
Optimizing production agents with Amazon Bedrock AgentCore Observability
As your AI agents move from prototype to production, the challenge shifts from getting them to work to keeping them fast and efficient. Learn how to use Amazon Bedrock AgentCore Observability and Amazon CloudWatch to find performance bottlenecks and diagnose memory issues in long-running agent sessions.
Source wire
Trending on Hugging FaceHub trending score · params · weight · vram
HFText generation
deepseek-ai
DeepSeek-V4-Flash-0731
MITSafetensors
1.3k likes15.4k downloads
HFVision + text
DavidAU
Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF
27B params25.0 GB262k ctxApache-2.0GGUF
≥32 GB VRAM1.2k likes1.2M downloads
HFVision + text
baidu
Unlimited-OCR
MITSafetensors
3.7k likes2.5M downloads
HFText to speech
owensong
Inflect-Micro-v2
Apache-2.0
352 likes1.6k downloads
HFmodel
unsloth
DeepSeek-V4-Flash-0731-GGUF
1M ctxMITGGUF
240 likes4.0k downloads
HFText generation
zai-org
GLM-5.2
MITSafetensors
4.7k likes1.7M downloads
HFText generation
Kwaipilot
KAT-Coder-V2.5-Dev
Apache-2.0Safetensors
379 likes10.8k downloads
RAG & Graphkind · repo · vector DB · memory
RAGRAG
Hugging Face
BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms
Research Papers
RAG
RAGRAG
Amazon
Market surveillance agent with LangGraph and Strands on AgentCore
Model Releases
RAG
RAGRAG
Mistral
Evaluating RAG with LLM as a Judge | Mistral AI
Model Releases
RAG
RAGGraph RAG
Amazon
AgentCore (June 2026): Web Search Tool is now Generally Available
Model Releases
Graph RAG
RAGRAG
Amazon
AgentCore (June 2026): Amazon Bedrock Managed Knowledge Base is now Generally Available
Model Releases
RAG
RAGRAG
Cohere
Sherlock AI Won AI Tinkerers Hackathon Using Cohere Rerank
Industry News
RAG
RAGRAG
Cohere
Five reasons enterprises are choosing RAG
Industry News
RAG
RAGRAG
Cohere
Command R: RAG at Production Scale
Industry News
RAG
Latest papersarXiv · field · preprint
HFResearch
Hugging Face Papers
SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them
HFResearch
HFResearch
Hugging Face Papers
MemHarness: Memory Is Reconstructed, Not Replayed
HFResearch
HFResearch
Hugging Face Papers
PhiZero: A World Model Built Around Physical Language
HFResearch
HFResearch
Hugging Face Papers
ACE-Data-0: Human-Centric Ambient Capture as Embodied Data Engine
HFResearch
HFResearch
Hugging Face Papers
VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System
HFResearch
HFResearch
Hugging Face Papers
Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion Transformers
HFResearch
HFResearch
Hugging Face Papers
ReToken: One Token to Improve Vision-Language Models for Visual Retrieval
HFResearch
HFResearch
Hugging Face Papers
Metis: Memory Foundation Model
HFResearch
Latest intel(470)
Industry NewsCohere
Cohere Signs EU AI Content Transparency Code
Cohere is among the first companies to sign the Code reflecting its commitment to compliance with the EU AI Act.
Model ReleasesAmazon Bedrock AgentCore Release Notes
AgentCore (July 2026): Gateway: Web Search connector version 1.2.0 adds request-level filters and target-level include list
The AgentCore Gateway Web Search Tool connector adds version 1.2.0 . At the target level, users can now configure a domain include list to restrict searches to a chosen set of domains, in addition to the existing exclude list. Both target-level lists now support up to 100 domains, expanded from the previous limit of 20 on the exclude list. At the request level, agents can pass an optional filters object on each tools/call request: domainFilter.include and domainFilter.exclude (up to 100 domains
Research PapersResearchHugging Face Papers
SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them
Vision-language models (VLMs) are increasingly used in embodied agents to interpret visual inputs, reason about spatial relationships, and make task-level decisions based on that reasoning. However, a fundamental capability mismatch remains: general VLMs can reason about the overall task but often miss the visual details that determine success, while specialist vision models can capture those details but cannot translate them into task-level decisions. In this work, we propose SpatialCLI, a fram
Research PapersResearchHugging Face Papers
MemHarness: Memory Is Reconstructed, Not Replayed
Retrieving past experiences has become a common strategy to enhance large language model agents. However, most existing memory-augmented agents treat retrieved experiences as static records to be replayed verbatim, injecting them into the context regardless of whether they align with the agent's current situation. This ``replay'' paradigm ignores the gap between the abstract, general nature of stored experience and the concrete, ever-changing states encountered at decision time, frequently causi
Research PapersResearchHugging Face Papers
PhiZero: A World Model Built Around Physical Language
We introduce PhiZero, a physical world model built around physical language, a compact discrete representation of world-state transitions. Existing physical world models typically predict future videos directly in pixel space, leaving the underlying world dynamics implicit within high-dimensional visual predictors. Motivated by humans' ability to abstract predictive structure from visual experience and organize it in natural language for explicit reasoning, we learn physical language from in-the
Research PapersResearchHugging Face Papers
ACE-Data-0: Human-Centric Ambient Capture as Embodied Data Engine
Embodied intelligence faces a fundamental data bottleneck. Models must capture how first-person perception, whole-body motion, dexterous manipulation, object state, sound, and touch evolve together as humans pursue goals over time. Existing datasets fragment this experience across viewpoints, modalities, or spatial scales, leaving the full perception-action loop only partially observed. We introduce the Ambient Capture Engine (ACE), a human-centric data engine that transforms real home environme
Research PapersResearchHugging Face Papers
VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System
Text-to-video models have achieved remarkable visual quality, yet they still struggle to generate physically consistent dynamics because the temporal evolution of a scene must be inferred implicitly from a highly compressed text prompt. Existing chain-of-thought approaches introduce intermediate plans or visual states, but these representations are typically non-executable or temporally sparse, limiting their ability to instantiate and control the complete spatiotemporal process. To address this
Research PapersResearchHugging Face Papers
Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion Transformers
Visual generation increasingly requires high-resolution images, long videos, and multimodal context, making the quadratic cost of full attention prohibitive. We introduce Chimera, a hybrid visual diffusion backbone with a principled scaling recipe. Chimera processes text, image, and video tokens in one raster-ordered stream without positional embeddings. It combines Kimi Delta Attention (KDA) for long-context state tracking with O(N) complexity, interleaved Multi-head Latent Attention (MLA) for
Research PapersResearchHugging Face Papers
ReToken: One Token to Improve Vision-Language Models for Visual Retrieval
Long visual context poses a challenge for vision-language models: performance degrades as the number of distractors grows, and processing all tokens at once is computationally infeasible under GPU memory constraints. We present ReToken, a single learnable embedding trained as an explicit retrieval target that selects a sparse set of query-relevant visual tokens from a pre-filled visual KV cache. Trained on only a small image-QA dataset, ReToken yields consistent gains across image and video benc
Research PapersResearchHugging Face Papers
Metis: Memory Foundation Model
Recent advances in AI agents have increasingly internalized native capabilities into their underlying foundation models, giving rise to multimodal foundation models and large reasoning models. However, agent memory is still primarily implemented through external modules, leaving the native memory capability largely unexplored. In this paper, we take a first step toward this direction by introducing memory foundation models, which empower foundation models with native memory capabilities. We form
Research PapersResearchHugging Face Papers
Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering
Recursive self-improvement (RSI) requires AI systems that improve the process of building AI (i.e., AI4AI); machine learning engineering (MLE) offers a concrete, executable testbed for studying this capability. We introduce OpenMLE, an open full-stack system for RSI research in MLE, spanning verifiable task environments with execution feedback (OpenMLE-Gym), operator learning (OpenMLE-RL), and long-horizon search (OpenMLE-Evo). On this stack we post-train Frontis-MA1 (35B) as a meta-evolution ag
Research PapersResearchHugging Face Papers
AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis
Chemistry literature synthesis often requires assembling specific findings scattered across many publications, yet existing literature-search systems primarily return ranked document lists. As a result, scientists and AI agents need to locate relevant information, verify their provenance, and assemble cross-paper answers manually. We present AskChem, a claim-centered infrastructure for cross-paper chemistry search. AskChem changes the unit of retrieval from the paper to the provenance-carrying c
Research PapersResearchHugging Face Papers
Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale
Computer-use agents learn from what their actions change, so training one needs applications it can act on, break and reset. The applications that matter most are login-gated and stateful, so synthetic environments stand in for them. Recent pipelines generate such environments in bulk, which moves the bottleneck from how many exist to what is inside each one. The returns, we find, come from three properties: how much behavioural depth an environment carries, whether it targets the interaction an
Research PapersResearchHugging Face Papers
Harness-G: A Graph-Structured Harness for Search Agents
Reinforcement learning (RL) search agents commonly model retrieval as free-form natural-language query generation and optimize multi-turn interactions using final-answer rewards. Current studies mainly improve training with denser or more structured credit signals, but rarely examine whether retrieval is properly formulated at the policy-environment interface. We observe pronounced retrieval aliasing during Search-R1 training: rollouts for the same question continue to generate distinct query st
Research PapersResearchHugging Face Papers
Flux-OPD: On-Policy Distillation with Evolving Contexts
Large language model training in open-ended domains lacks verifiable rewards, making task preferences difficult to formalize as effective supervision. Contexts can convey such preferences, yet provide little additional supervision once distilled into the student, motivating contexts that evolve with student performance. However, directly using evolving contexts as in-training supervision results in an unstable distillation target and conflicting distributions, requiring mechanisms to stabilize t
Research PapersResearchHugging Face Papers
BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms
Retrieval-augmented generation (RAG) spans lexical and dense retrieval, graph-based indexing, and agentic search, but these paradigms are usually evaluated on different benchmarks at one corpus size, leaving their accuracy-cost scaling unclear. To bridge this gap, we present a controlled study that varies corpus size along 28 strictly nested tiers spanning roughly 450-fold, while holding questions and a fixed bedrock of relevant and adversarial documents unchanged. Under one reader model and one
Research PapersResearchHugging Face Papers
Beacon: Knowing When and How to Perform Agentic Visual Reasoning
The fundamental goal of agentic visual reasoning is to improve the success rate of multimodal large language models (MLLMs) on complex tasks, rather than merely equipping them with a sophisticated yet inefficient reasoning paradigm. In this work, we rethink agentic visual reasoning through two key dimensions of tool use: Mode Adaptiveness (MA) and Tool Effect (TE). Mode Adaptiveness characterizes whether an MLLM can recognize when tools are truly necessary and invoke them accordingly, thereby av
Research PapersResearchHugging Face Papers
RefCaptioner: Multi-Reference Image-Grounded Video Captioning
Existing video captioning models generate natural descriptions of video content but cannot explicitly ground local visual elements to multiple reference images. We introduce multi-reference image-grounded video captioning, a new task requiring factual video descriptions with phrase-level reference grounding, and propose RefCaptioner, a two-stage post-training framework for this task. RefCaptioner combines mixed-data SFT with Hierarchical Coverage-Discounted GRPO to jointly improve reference sele
Research PapersResearchHugging Face Papers
Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents
GUI agents have the potential to become a general purpose executor over existing digital devices. To advance them toward real-world use, we envision agents that operate reliably on real devices, execute workflows across platforms, combine GUI interaction with CLI execution, complete long-horizon tasks, proactively initiate useful services, and autonomously improve their capabilities with minimal human effort. Guided by this vision, we present Qwen-UI-Agent, a real-world centric foundation GUI ag
Research PapersResearchHugging Face Papers
Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory
Decoder-only language models entangle long-term memory and reasoning in a single parameter set, making it difficult to scale memory capacity independently. Memory Decoder introduces a parametric long-term memory module but only studies it at a relatively small scale. In this work, we present Memory Decoder at Scale, scaling memory models up to 6.9B parameters and pretraining them on 300B tokens. At this data scale, the combined cost of indexing and search makes a standard Faiss pipeline infeasib