AllyshipContent Radar

News 2803

Chủ đề cộng đồng đang thảo luận

Crawl live-1795079700000 · 16:15 19 thg 11, 2026 · Xuất bản 16:30 19 thg 11, 2026

187 / 2803 chủ đề đạt ngưỡng 55 trong khoảng này.

41

ARISE: Practical Self-Evolving Memory for Accurate and Cost-Efficient Enterprise Agents

55

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Jiangyun Zhang, Zhou Tang, Kristen Surrao, Zhiyu Chen, Albert Guan, Tor Nitayanont, Yupei Zhang, Roopali Singh, Yunkai Xiao, Shreya Pandit, Julia Huang, Shayan Ali Akbar, Erwin Cornejo, Yuan Li, Yi Zhang 1 bài viết · arXiv cs.AI
Nguyên văn nguồn
Chi tiết nguồn

arXiv:2611.23588v1 Announce Type: new Abstract: Enterprise LLM agents operate in dynamic environments where foundation models evolve rapidly, workflows update frequently, and deployments need to satisfy accuracy and cost requirements. We propose ARISE (Agent Refinement through Iterative Self-Evaluation), a practical memory architecture in which the agent's memory evolves from its own failures without updating model weights, tools, or workflow logic. ARISE uses the model itself or a teacher model to attribute the failures and propose corrections. Then, ARISE keeps the corrections as retrievable micro memory, consolidates them into macro rules, and accepts a rule update only if held-out accuracy rises. Across 14 enterprise-workflow domains from SOP-Bench and $\tau^2$-bench using 5 models, ARISE-Teacher, which uses Claude Opus 4.6 for attribution and consolidation, gains 10.9 pp over the baseline on SOP-Bench and 5.8 pp on $\tau^2$-bench. ARISE-Teacher also outperforms GEPA by 4.5 pp on $\tau^2$-bench and 1.4 pp on SOP-Bench. With the deployment model as its own attributor, ARISE-Self still gains 10.0 pp on SOP-Bench. ARISE-Teacher uses 4.0% fewer model calls and 5.2% fewer output tokens at comparable per-task cost (-1.0%).

42

RefinementGuard: Counterexample-Directed Semantic Qualification for Hidden Agent-Tool Execution

55

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Adhyayan Veer Singh, Fanjiang Ye, Yuke Wang 1 bài viết · arXiv cs.AI
Nguyên văn nguồn
Chi tiết nguồn

arXiv:2611.23611v1 Announce Type: new Abstract: Tool runtimes can lower an agent-selected operation into a hidden parallel graph, reducing latency and context while risking semantic mistranslation. We introduce RefinementGuard: translation validation for hidden, effectful agent-tool lowerings, coupled to artifact-bound, fail-closed runtime admission. Qualification compares a candidate graph with an independent reference on isolated state using explicit parent-operation obligations. We evaluate two repository-level contracts, bug localization and patch validation, on controlled repositories. Among 100 activated, non-equivalent development/qualification faults adjudicated by one human, parent-semantic validation rejects 49/100 (operator-cluster bootstrap 95% CI [33.7%, 64.8%]). The objective is selective admission, not maximum mutation rejection: exact equality rejects 100/100 faults but also all 60 valid variants, whereas obligation-based validation accepts 60/60; its 51 residual misses identify concrete specification gaps. On a frozen disjoint input split, the held-out B2-B3 result is localization-only because 21 patch mutants fail structurally; B3 rejects 38/56 localization defects. In a controlled asynchronous-delay regime, the localization serial/guarded median-latency ratio is 4.50x, and hidden execution exposes 74.3% less parent-visible context than visible execution. Patch validation shows no demonstrated speedup; zero-delay runs expose overhead. End-to-end qualification thus detects lower-layer misses while preserving localization's parallelism.

43

Searching the Pareto Front: Multi-Objective Retrieval for Heterogeneous Scientific Modalities

55

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Song Young Oh, Nesar Ramachandra, Bin Xia, Ian Foster, Kyle Chard 1 bài viết · arXiv cs.AI
Nguyên văn nguồn
Chi tiết nguồn

arXiv:2611.23639v1 Announce Type: new Abstract: In cosmology, surveys span different sky regions and wavelength ranges, resulting in uneven modality coverage across observational datasets. Such heterogeneity can be addressed through either multimodal foundation models (FMs), which learn shared embedding spaces, or independently learned modality embeddings combined via late fusion. We investigate whether the latter provides an adaptive alternative to FM-based scientific retrieval. We evaluate this approach on a galaxy retrieval task spanning diverse modalities--history of star formation, spectra of light emitted, and multi-wavelength observations from two telescopes--comparing an FM baseline with separately trained embeddings fused through multi-objective optimization based on Pareto optimality. We find that the FM baseline achieves strong embedding-space proximity, but our method preserves modality-specific distance structure that allows scientists to inspect which physical signals drive similarity. Our method also achieves improved fidelity in raw-data space: across six measured properties, its nearest neighbor is 8% closer to the query on average than that retrieved by kNN in the FM embedding space (spread 0.128 vs. 0.139). These results suggest that multi-objective retrieval can surface astrophysically coherent candidates that single-objective search alone may overlook.

44

Evaluating Governed LLM-Driven ML Experimentation: Lifecycle, Provenance, and Failure Metrics

55

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Dowling Wong 1 bài viết · arXiv cs.AI
Nguyên văn nguồn
Chi tiết nguồn

arXiv:2611.23678v1 Announce Type: new Abstract: Autonomous agents that run ML experiments are usually judged by the best score they reach. That score says nothing about how it was reached: whether the agent stayed within the files it was allowed to edit, whether failed trials were kept or silently dropped, and whether each keep or discard decision can be traced to its evidence. We propose evaluating such systems on their experimental process as well as their outcome, and we build a governed harness that makes this possible. A control plane, not the LLM that proposes changes, owns each trial's lifecycle, checks its edit scope, decides keep or discard, and appends one record per trial to an append-only ledger. Governance metrics such as the invalid-action rate, the repeated-bad rate and provenance completeness are computed from that ledger. Across six ML tasks, from synthetic logistic regression to language-model training, and 1,445 trials, the same contract applied unchanged. The ledger exposed failures that a task score hides: a no-memory arm in which all 120 trials failed, a benchmark adapter whose bounded proposals ran out, and a reset failure that reproducibility hashes revealed, after which the affected campaigns were rerun. In a matched counterfactual, a loop that logs only successful trials left no record of 43 of 50 trials, while the governed ledger recorded all 50. Memory ablations show that memory's effect on repeated bad proposals depends on the task. We release the ledgers of all 1,445 trials, so that every number reported for them can be recomputed.

45

Auditable Clinical Support with Decision Agents

55

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Tiancheng Bao, Riga Wu, Jan Wienhold, Sebastian Billig, Patrick Winnersbach, Hsuan-Chih Chen, Akis Giannoukos, Jiayang Li, Li Shen, Gary Weissman, Eduardo J. Mortani Barbosa Jr, Dyke Ferber, Jakob Nikolas Kather, Christos Davatzikos, Daniel Truhn, Tianyu Han 1 bài viết · arXiv cs.AI
Nguyên văn nguồn
Chi tiết nguồn

arXiv:2611.23700v1 Announce Type: new Abstract: Clinicians reviewing a diagnostic work-up will ask what was considered at each step and why the assessment changed. Agents powered by free text can reach physician-level diagnostic accuracy, but their written reasoning does not always reflect the factors that went into the decision. Here, we present Decision2Care, a decision agent that works up the acutely ill patient without producing any text. A decision model assigns a probability to each permitted EHR action, and fixed rules carry out the most probable one. We evaluated Decision2Care on the records of 546 emergency admissions across 12 diseases. Decision2Care reached a diagnostic accuracy of 86.5%, compared with 86.1% for the MIRA-v2 agent, and required a median of 2.2 s per work-up, compared with 92-100 s. Each work-up tracked which options Decision2Care was considering at each step. In 10 of the 12 diseases, the differential diagnosis changed most at the test on which the guideline bases the diagnosis. Where Decision2Care was most confident after a single work-up, all but four of its diagnoses were correct (98.5%). We traced each of these four errors back to a single imaging report. Three of them were corrected when that report was removed. The same kind of decision was used to select the treatments, and Decision2Care's drug orders were judged guideline-adherent more often than MIRA-v2's. In emergency patients, its prediction of death was comparable to that of three intensivists on the same cases. In five of the eight intensive care cohorts, it exceeded the best of the three 24-h severity scores within 2-6 h of records. Our results show that decision agents can carry out clinical work-ups while recording the options, probabilities, and execution rules behind each action for audit.

46

KnowMe Paper Radar: Lightweight Discovery of Promising Papers in the Age of Autoresearch

55

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Zhuo Chen, Jian Wang, Jinjie Gu, Lijun Wu 1 bài viết · arXiv cs.AI
Nguyên văn nguồn
Chi tiết nguồn

arXiv:2611.23702v1 Announce Type: new Abstract: The growing volume of topically similar papers makes it difficult to identify new work that can offer useful research insights or methodological guidance. We present KnowMe Paper Radar, a lightweight discovery tool that combines multiple sources of evidence into personalized reading priorities. Users specify topics, priorities, exclusions and dates; the system brings together topical relevance, recency, author research histories, collaboration paths and direction-specific institutional context. By exposing each score component and its supporting sources, KnowMe helps readers select promising papers for their current questions and discover relevant work beyond familiar authors. Automatic acquisition, version merging and graph-cache reuse keep this workflow convenient without large language model (LLM) inference during ordinary use. Experiments on 174,640 acquired records show more than threefold faster repeated context preparation, while cached abstracts improve normalized discounted cumulative gain at rank 10 (NDCG@10) from 0.412 to 0.598 on expert-judged retrieval tasks. Complementary analyses examine how the same accumulated records support semantic retrieval, research-history modeling and literature-grounded planning. A browser interface and a structured command-line interface (CLI) make these capabilities available to both researchers and research agents, positioning KnowMe as a practical upstream tool for literature-informed recursive self-improvement (RSI) workflows.

47

Modeling LLM Reasoning Dynamics with Structural Representations

55

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Ilia Karpov, Andrey Atamanyuk, Dmitry Ilvovsky, Aleksandr Anokhin, Alex Elizov, Dmitry Zagorulkin, Sergei O. Kuznetsov 1 bài viết · arXiv cs.AI
Nguyên văn nguồn
Chi tiết nguồn

arXiv:2611.23749v1 Announce Type: new Abstract: Language-model reasoning alternates between sustained activities and local operations. We study how this temporal structure predicts continuation and the computation needed to analyze it. T/E/S combines text, local events, and spans of activity. Across reasoning and information-seeking tasks, events and spans improve next-outcome prediction in 70 of 76 evaluation groups for a Transformer and 74 of 76 for Qwen with LoRA. Span duration and preceding events are associated with transitions, and retaining event history across span boundaries improves prediction. We formulate budget-allocation counting and action-conditional continuation queries, prove counting hardness under explicit encodings, and derive conditions for affordable decision certification. In finite-process experiments, bounds that cancel shared continuation mass recover the same optimal actions as full dynamic programming while reducing mean inference CPU time by 77.7%. On 71 held-out HotpotQA and MuSiQue questions, a compact structural observer improves prediction of whether a fixed inference procedure finishes within a CPU allowance: Brier loss falls from 0.0836 to 0.0756. An annotation audit identifies substantial errors in that observer, separating this computational result from semantic validation of its features.

48

Thinking Fast, Anywhere: One System-1 for the Decision Points of Any Agent Workflow

55

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Rui Li, Liyang He, Zheng Zhang, Zhenya Huang, Qi Liu 1 bài viết · arXiv cs.AI
Nguyên văn nguồn
Chi tiết nguồn

arXiv:2611.23751v1 Announce Type: new Abstract: Autonomous LLM agents incur substantial cost and latency by invoking a large model (System-2) at every step, even when many intermediate actions choose among a small set of known candidates. Existing dual-system agents offload such decisions to a lightweight System-1 model, but rely on workflow-specific hooks authored per environment. We present AnyS1, a framework that turns human-authored procedural skills, whose instructions naturally specify where choices arise and which options apply, into a shared, domain-general source of decision points. Offline, AnyS1 mines grounded enumerable decisions across over 1,000 public skills, gathers execution-grounded trajectory states inside isolated containers to construct Any-DP, and trains a single calibrated 4B pointer System-1 with label smoothing. At run time, compiled workflows resolve routine decisions in one forward pass and fall back to System-2 when confidence falls below a calibrated threshold. Across three unseen benchmarks and distinct System-2 model families, AnyS1 preserves task reliability while cutting episode cost by 75-91% and model-call time by 63-92% relative to an uncompiled System-2 agent, and maintains performance under zero-shot threshold transfer.

49

Continual Tool-Space Extension Learning for Multimodal Agents

55

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Jinbae Seo, Jungin Park, Hyunsung Jang, Namkoo Ha, Jiyoung Lee, Kwanghoon Sohn 1 bài viết · arXiv cs.AI
Nguyên văn nguồn
Chi tiết nguồn

arXiv:2611.23810v1 Announce Type: new Abstract: Multimodal agents largely rely on generic tools such as cropping, search, and code execution, leaving specialist vision models outside their tool space. However, bringing such a model into an already trained agent is not straightforward. The challenge is to learn each new tool efficiently while retaining the ability to use existing ones. This work proposes COTEX, continual tool-space extension learning, that adds new tools at efficient adapter-level cost. COTEX locates two sets of parameter directions; one triggers a tool call and thereby opens a multi-turn reasoning trajectory, while the other determines which tool is chosen. The adapter of a new tool is restricted to the calling directions that leave earlier tool choices unaffected by orthogonal constraint. We further introduce a protocol that converts specialist models' existing task-specific annotations into verified tool-use trajectories. Experiments on two representative agents and three specialist tools show gains on ten vision-language benchmarks, with at most a 0.3-point drop on existing tools.

50

Metrics-in-the-Loop: Complexity Feedback Reshapes Agent-Written Code

55

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Nicolas Chapados, Jean-Fran\c{c}ois Gagn\'e, Nouha Dziri 1 bài viết · arXiv cs.AI
Nguyên văn nguồn
Chi tiết nguồn

arXiv:2611.23817v1 Announce Type: new Abstract: Coding agents now write whole codebases in long autonomous runs, guided mainly by whether their tests pass. Yet passing tests alone does not reveal accumulating complexity or gaps in test coverage, which then persist as agents extend their own code. We introduce metrics-in-the-loop, an inference-time intervention that gives agents in-flight feedback: cheap, automatically computed code metrics injected into the agent's context during the trajectory. After each code-changing agent turn, we insert short feedback messages naming changed functions whose cyclomatic complexity exceeds a limit (complexity feedback) or changed lines that are skipped by tests (coverage feedback), giving the agent the opportunity to refactor code or strengthen tests before continuing. We run extensive experiments and ablations comparing several interventions across three long-horizon coding benchmarks and four strong models. We find that complexity feedback significantly reduces erosion, a measure of complexity concentration of code, without affecting held-out correctness of the code. Broadly, our experiments investigate a practical form of agent "re-railing", where timely, actionable measurements redirect agents before weaknesses become the foundation they keep building on. As agents scale to codebases with millions of lines, such interventions become critical to sustaining effective development and long-term code maintainability.

51

A System 1 Decision Model for Medical Multiple-Choice Questions Built on Frozen Language Models

55

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Pavan Kumar Mantha 1 bài viết · arXiv cs.AI
Nguyên văn nguồn
Chi tiết nguồn

arXiv:2611.23832v1 Announce Type: new Abstract: A System 1 model answers a multiple-choice question in a single pass. A frozen language model turns the question and each option into vectors, two small, trained heads place them in a shared space, and the closest option wins. The design has been shown on agent decisions, but we are not aware of a study of how far it goes on exam questions that need medical knowledge, where the right option is often no more similar to the question than the wrong ones. We rebuilt the recipe from scratch for MedMCQA and trained only two projection heads and one temperature on top of frozen Qwen3.5-0.8B, Granite-4.2-3B and Qwen3-8B, using a contrastive loss with in-batch and hard negatives and a mask for repeated answers. With plain last-token vectors, both small encoders answer about one question in three correctly (33.1% and 33.0% on 3,842 held-out questions, where chance is 25.0%). Writing each text inside a one-word-summary prompt and lowering the learning rate of the heads raised this to 41.7% and 42.5% for the two small encoders and to 46.0% +-0.2 (three seeds) for Qwen3-8B. Shuffling the questions against the options returns accuracy to chance, so the heads do use the question. Flan-PaLM and Med-PaLM 2 report 57.6% and 72.3% on MedMCQA under a different protocol, so ours is a cheap, fast baseline and not a competitive system. We also say what our evidence cannot show: validation gains were about 1.7 to 2 times the test gains, and we could not separate the effect of reading several encoder layers from the other changes.

52

RoboBuilder: Agentic Robot Co-Design with Real-world Video Feedback in the Loop

55

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Ghadi Nehme, Dahyun Nam, Akshay Govind Srinivasan, Faez Ahmed 1 bài viết · arXiv cs.AI
Nguyên văn nguồn
Chi tiết nguồn

arXiv:2611.23855v1 Announce Type: new Abstract: Can AI agents design robots that work in the real world? We introduce RoboBuilder, a benchmark in which coding agents co-design a robot's hardware and program from standard parts, motors and a custom 3D-printed part, and every design that passes in simulation is built and tested on a physical course. Simulation alone is not enough: under public part data, none of 15 initial passing designs crossed the real course, so an agent learns the simulator from measurements it requests and videos of real runs. Across four frontier coding agents, ten obstacles at three difficulty levels, 16,427 simulations of 12,774 distinct robots and 135 physical robots built in an estimated 240 hours, agents solve nearly all easy obstacles and invent mechanisms our search baselines do not reach, but falter at harder levels, when one robot must cross every obstacle, and in the real world, where 66% of simulated passes hold across all levels. Closing the loop helps: shown a video of its real failure, an agent redesigns the robot, sometimes correcting its simulator, and removes 72% of level-1 and level-2 failures. RoboBuilder measures progress toward agents that engineer real machines. Project Page: https://ghadinehme.com/robobuilder.github.io/

53

使用 Gemini 4 Neon 的渠道:

55

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

oran_ge 0 bài viết · X
Nguyên văn nguồn
Chi tiết nguồn

使用 Gemini 4 Neon 的渠道: 谷歌官方订阅 Pro 以上可用: https://gemini.google/subscriptions/ Cola 会员 Plus 以上可用:https://colaos.ai/ Openrouter 买 API:https://openrouter.ai

54

b12532

55

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

github-actions[bot] 1 bài viết · ggml-org/llama.cpp releases
Nguyên văn nguồn
Chi tiết nguồn

<details open=""> <p>opencl: allow adjusting KV padding in decomposed FA (<a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="6462356977" data-permission-text="Title is private" data-url="https://github.com/ggml-org/llama.cpp/issues/32522" data-hovercard-type="pull_request" data-hovercard-url="/ggml-org/llama.cpp/pull/32522/hovercard" href="https://github.com/ggml-org/llama.cpp/pull/32522">#32522</a>)</p> <p>Assisted-by: Codex</p> </details> <p><strong>Website:</strong></p> <ul> <li><a href="https://llama.app" rel="nofollow">https://llama.app</a></li> </ul> <p><strong>Attestations:</strong></p> <ul> <li><a href="https://github.com/ggml-org/llama.cpp/attestations/69491345">https://github.com/ggml-org/llama.cpp/attestations/69491345</a></li> </ul> <p><strong>macOS/iOS:</strong></p> <ul> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/llama-b12532-bin-macos-arm64.tar.gz">macOS Apple Silicon (arm64)</a></li> <li>macOS Apple Silicon (arm64, KleidiAI enabled) <a href="https://github.com/ggml-org/llama.cpp/pull/23780" data-hovercard-type="pull_request" data-hovercard-url="/ggml-org/llama.cpp/pull/23780/hovercard">DISABLED</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/llama-b12532-bin-macos-x64.tar.gz">macOS Intel (x64)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/llama-b12532-xcframework.zip">iOS XCFramework</a></li> </ul> <p><strong>Linux:</strong></p> <ul> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/llama-b12532-bin-ubuntu-x64.tar.gz">Ubuntu x64 (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/llama-b12532-bin-ubuntu-arm64.tar.gz">Ubuntu arm64 (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/llama-b12532-bin-ubuntu-s390x.tar.gz">Ubuntu 24.04 s390x (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/llama-b12532-bin-ubuntu-26.04-s390x.tar.gz">Ubuntu 26.04 s390x (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/llama-b12532-bin-ubuntu-zdnn-s390x.tar.gz">Ubuntu 26.04 s390x (zDNN)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/llama-b12532-bin-ubuntu-vulkan-x64.tar.gz">Ubuntu x64 (Vulkan)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/llama-b12532-bin-ubuntu-vulkan-arm64.tar.gz">Ubuntu arm64 (Vulkan)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/llama-b12532-bin-ubuntu-cuda-12.8-x64.tar.gz">Ubuntu x64 (CUDA 12)</a> - <a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/cudart-llama-b12532-bin-ubuntu-cuda-12.8-x64.tar.gz">CUDA 12.8 libraries</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/llama-b12532-bin-ubuntu-cuda-13.5-x64.tar.gz">Ubuntu x64 (CUDA 13)</a> - <a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/cudart-llama-b12532-bin-ubuntu-cuda-13.5-x64.tar.gz">CUDA 13.5 libraries</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/llama-b12532-bin-ubuntu-cuda-13.5-arm64.tar.gz">Ubuntu arm64 (CUDA 13)</a> - <a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/cudart-llama-b12532-bin-ubuntu-cuda-13.5-arm64.tar.gz">CUDA 13.5 libraries</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/llama-b12532-bin-ubuntu-rocm-10.0-x64.tar.gz">Ubuntu x64 (ROCm 10.0)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/llama-b12532-bin-ubuntu-openvino-2026.4.1-x64.tar.gz">Ubuntu x64 (OpenVINO)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/llama-b12532-bin-ubuntu-sycl-fp32-x64.tar.gz">Ubuntu x64 (SYCL FP32)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/llama-b12532-bin-ubuntu-sycl-fp16-x64.tar.gz">Ubuntu x64 (SYCL FP16)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/llama-b12532-bin-linux-arm64-snapdragon.tar.gz">Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU)</a> - <a href="https://github.com/ggml-org/llama.cpp/blob/master/docs/backend/snapdragon/linux.md">setup guide</a></li> </ul> <p><strong>Android:</strong></p> <ul> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/llama-b12532-bin-android-arm64.tar.gz">Android arm64 (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/llama-b12532-bin-android-arm64-snapdragon.tar.gz">Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU)</a> - <a href="https://github.com/ggml-org/llama.cpp/blob/master/docs/backend/snapdragon/README.md">setup guide</a></li> </ul> <p><strong>Windows:</strong></p> <ul> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/llama-b12532-bin-win-cpu-x64.zip">Windows x64 (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/llama-b12532-bin-win-cpu-arm64.zip">Windows arm64 (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/llama-b12532-bin-win-opencl-adreno-arm64.zip">Windows arm64 (OpenCL Adreno)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/llama-b12532-bin-win-cuda-12.4-x64.zip">Windows x64 (CUDA 12)</a> - <a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/cudart-llama-bin-win-cuda-12.4-x64.zip">CUDA 12.4 DLLs</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/llama-b12532-bin-win-cuda-13.5-x64.zip">Windows x64 (CUDA 13)</a> - <a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/cudart-llama-bin-win-cuda-13.5-x64.zip">CUDA 13.5 DLLs</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12532/lla

  • b12532 ggml-org/llama.cpp releases · 19 thg 11, 2026
57

Code World Model 2.0: Towards Infinite Controllable Video Generation

86

12 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · 9 tương tác đã đo · Nguồn crawl

Ruoyu Wang, Hao Zhong và 10 nguồn khác 1 bài viết · Hugging Face Papers, X
Biên tập tiếng Việt
Chi tiết nguồn

Bài báo mô tả cách các “visual proxies” tách việc mô phỏng trạng thái thế giới khỏi sinh video hiện thực, cung cấp một giao diện điều khiển cho tạo clip ngoại tuyến và streaming tương tác thời gian thực. Họ nêu hai thách thức: các proxy thay đổi theo mức độ tương tác, và suy luận streaming cần chạy trong vài bước nhân quả mà không tích lũy trôi do lịch sử tự sinh.

Visual proxies decouple explicit world-state simulation from photorealistic video synthesis, offering a controllable interface for both offline clip creation and real-time interactive streaming. Yet a practical renderer must address two challenges. Upstream proxies vary from coarse layouts to fine articulated geometry depending on the interaction, and streaming inference must operate in a few causal steps without accumulating drift across self-generated history. We present Invoker-Render, pairing a bidirectional creation model with a causal four-step streaming model under a shared conditioning interface over structural proxies, an appearance reference, and language. Trained on an aligned approximately 200-hour multi-granularity corpus, Invoker-Render honors fine geometric constraints when supplied while synthesizing plausible local motion under coarse proxies, enabling runtime selection of input detail. To bridge bidirectional creation and real-time streaming without compounding step compression and rollout drift, we introduce Progressive Forcing (ProForcing). ProForcing first trains a causal predictor and distills it into a four-step renderer using histories derived from training videos. Training then shifts to continuous self-generated rollouts. A pipelined serving stack supports efficient streaming inference. Experiments show versatile control across proxy families, granularities, and camera paths, consistent gains over recent streaming baselines, and stable 30-minute racing rollouts that preserve scene and subject appearance.

  • We present Invoker-Render, pairing a bidirectional creation model with a causal four-step streaming model under a shared conditioning interface over structural proxies, an appearance reference, and language.
  • We present Invoker-Render, pairing a bidirectional creation model with a causal four-step streaming model under a shared conditioning interface over structural proxies, an appearance reference, and language.
  • To bridge bidirectional creation and real-time streaming without compounding step compression and rollout drift, we introduce Progressive Forcing (ProForcing).
  • Experiments show versatile control across proxy families, granularities, and camera paths, consistent gains over recent streaming baselines, and stable 30-minute racing rollouts that preserve scene and subject appearance.
58

So now a small 300MB adapter makes your local 27B coding model dramatically better!

55

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

teksedge 0 bài viết · X
Nguyên văn nguồn
Chi tiết nguồn

So now a small 300MB adapter makes your local 27B coding model dramatically better! Hugging Face released an RL-trained LoRA adapter for Qwen3.8-27B, specifically optimized for OpenCode. And the reported results are impressive! SWE-bench Pro (hard 51 tasks): 🔴 Original → 35.3% 🟢 With LoRA → 51.0% 👈 Terminal-Bench 2.1: 🔴 Original → 46.4% 🟢 With LoRA → 52.4% 👈 Median agent turns on tasks both solved: 🐌 Original → 48 turns 🚀 With LoRA → 13 turns 👈 That's a 15.7% improvement on the selected SWE-bench Pro tasks and 73% fewer agent turns on shared solves. With thinking disabled, the adapted model reportedly approaches or exceeds the original model running at maximum reasoning effort, using 6–8× fewer generated tokens per task in the team's comparison. The best part? 💾 Adapter → ~300MB 🧠 Base model → Qwen3.8-27B 🔓 License → Apache 2.0 💻 Local inference → llama.cpp 🛠️ Coding harness → OpenCode 📦 GGUF adapter available Just a small adapter teaching an existing model to use coding tools more effectively. Video source: @HuggingFace Media

60

Pyrefly v1.5.0

61

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 8 tương tác đã đo · Nguồn crawl

fishgoesblub 1 bài viết · HN: GPT
Nguyên văn nguồn
Chi tiết nguồn
41–60 / 187
Trang 3 / 10