Skip to content
AI NEWS JOURNAL
AI, IN PERSPECTIVE

Search AI news

Search headlines, summaries and articles to connect the dots.

Newest first

Release v5.24.0

Hugging Face Transformers v5.24.0 introduces several new models including Inkling 2 Mini, Apertus 1.5, WavTokenizer, Dory, HY4-VL, Omnilingual ASR, Lara Mini, SarvamMLA, SarvamMoE, and EXAONE. The release features a major breaking change renaming `past_key_values` and `cache_params` to `cache` across the library, standardizing cache handling. Multimodal models now return shared output classes instead of model-specific ones. Additional updates include improvements to generation, continuous batching, chat templates, pipelines, vision and audio processing, quantization, parallelization, exporters, and numerous bug fixes.

Introducing harness adapters: adapt your favorite model to your harness to improve performance and cost

Training Qwen3.8-27B with reinforcement learning inside custom agent harnesses (Pi, OpenCode, Hermes Agent) using LoRA adapters significantly improves performance and efficiency on targeted coding benchmarks. The adapted models achieve higher pass rates with fewer tool calls and tokens compared to the base model, even when evaluated under different harnesses. A merged 'super-adapter' maintains strong results across all three harnesses, demonstrating transferable capabilities. The full training pipeline—including task generation via Hub, validation with OpenEnv, and efficient AsyncGRPOTrainer—is made publicly available for reproducibility.

Why your fine-tuning job takes longer than the FLOPs say

A study analyzing 272 production supervised fine-tuning jobs on NVIDIA H200 GPUs found that traditional FLOP-based estimates explain only 31% of actual training duration (R² = 0.31, MAE 12.41 h). In contrast, a CatBoost regressor using pre-dispatch job configuration features—including evaluation cadence, checkpoint policy, and per-GPU load—achieved R² = 0.98 with a mean absolute error of 1.71 h and median error of 0.51 h in cross-validation. The model outperforms analytical baselines by capturing overheads beyond compute, such as I/O contention and non-linear interactions between configuration variables. Results highlight the importance of training-specific signals and suggest that scheduling accuracy improves significantly when predictors account for operational overheads.

Time-Series Models in the Streamhouse: A New Frontier and Use Cases

IBM's time-series foundation models, with over 50 million downloads, are now natively integrated into Confluent's platform, enabling real-time forecasting, anomaly detection, and optimization on streaming data using SQL. These models run on CPUs in both cloud and on-premises environments, supporting mission-critical applications across manufacturing, retail, banking, and airlines by delivering timely insights closer to decision-making points. The integration leverages Apache Flink and Confluent’s Streamhouse architecture to process data streams, apply AI-driven intelligence, and enable actions such as production optimization, fraud detection, supply chain planning, and trading execution—all in real time.

Small Open-Weight Language Models for Crowd Decision-Making: Capabilities and Limits of Output-Level Fusion and Linguistic Aggregation

arXiv:2611.17589v1 Announce Type: new Abstract: Small open-weight language models can run crowd decision-making (CDM) on an institution's own infrastructure, which keeps the checkpoint, the inference settings and the opinions under its control. Their judgements vary across repeated queries; whether repeating and aggregating them, often through the 2-tuple linguistic representation, settles the decision rather than the labels is untested. Five open-weight models of 8-36B total parameters on one consumer GPU and a hosted reference classify 474 TripAdvisor reviews of four London restaurants ten times each; three open-weight models repeat the protocol on 600 reviews of twelve Madrid restaurants. Continuous evaluations preserve resolution: snapping each review leaves 5 distinct values against 21-65, and snapping at every level at most two collective values. Sensitivity to the participants persists once run-to-run variability is reduced: in London, redrawing the reviewers keeps the winner on 47-81% of replicas against 86-100% for redrawing the runs. With simultaneous intervals over every pair of alternatives under crowd resampling, no system on either corpus names a single winner: in London every system keeps all four restaurants as candidates, and in Madrid the candidate sets hold five to eight of the twelve. Extra runs and output-level fusion stabilize the winner but do not remove that sensitivity, and the fusion does not beat its best member. The three larger open-weight models name the hosted reference's London winner and at least match its per-review correlation with the reviewers' stars, so small open-weight models can support local CDM, reported as candidate sets with margins rather than forced rankings.

Build a Robot Pick-and-Place Simulation with SimReady Assets

This walkthrough demonstrates how to create a beverage can pick-and-place task using the UR17G robot arm, Robotiq 2F-140 gripper, and a beverage can in Isaac Sim. The process involves downloading SimReady assets from SimReady Central on Hugging Face, assembling the robot and gripper, validating joint and physics settings, and using an AI agent to generate and run control code for the task. The simulation tests grasp accuracy, object stability during movement, and placement precision, with validation reports confirming compliance with SimReady profiles. The workflow supports reuse of validated assets and encourages developers to contribute their own SimReady-compatible robotics content.

XYBench: Helping with the problem behind the question

XYBench, a benchmark of 8,115 real-world questions spanning programming and everyday tasks, tests AI assistants' ability to recognize and respond to users' misconceptions—such as asking how to thicken frosting when the real issue is warm cupcakes. Developed with researchers from Carnegie Mellon, NVIDIA, and Johns Hopkins, XYBench measures whether models identify underlying goals (X), address them effectively, and steer users away from flawed approaches (Y). Evaluations of models like Claude Sonnet 4.6, GPT-5, Gemini 3.1 Pro, Qwen3.5-9B, and DeepSeek-V4 Pro showed they frequently focused on the stated request rather than the actual goal, with limited success in misconception identification. Human reference answers outperformed all models, highlighting a gap in pragmatic reasoning. The benchmark uses automated and human evaluation to assess pragmatic solution, emphasis, and misconception identification, offering a tool for researchers to improve AI assistants’ ability to provide helpful advice even when users ask the wrong question.

LLMON: An LLM-Native Markup Language, now in Granite 4.1 3B and 8B

IBM has introduced LLMON (LLM Object Notation), a new markup language designed to explicitly communicate structure and semantics to large language models. Built to address issues like prompt injection attacks and brittle behavior in smaller models, LLMON uses reserved special-token delimiters to mark semantically coherent components such as instructions, data, and requirements, enabling precise binding between them. Two experimental preview models—granite-4.1-3b-LLMON-preview and granite-4.1-8b-LLMON-preview—are now available, alongside a GitHub repository with conversion tools, workflows, and examples. LLMON enhances robustness by separating instruction from data, reducing indirect prompt injection success rates nearly to zero while maintaining performance comparable to standard Granite 4.1 Instruct models. It also supports custom schemas via LoRA fine-tuning, as demonstrated in ScienceWorld and tool-calling agent use cases. The approach is distinct from JSON, which lacks model-friendly structure, and complements existing chat templates by adding semantic clarity across roles.

LLMs and the Homogenization of Teaching

arXiv:2611.14828v1 Announce Type: new Abstract: Large language models (LLMs) are known to lack diversity in open-ended text generation, a limitation that is especially consequential in education, where homogeneity can narrow the kinds of thinking and disciplinary work students are invited to do. We study diversity in two educational generation tasks: math items and essay feedback. We compare frontier and open-weight models with human-authored reference distributions using lexical, semantic, and domain-grounded measures. For math, we examine the mathematical activities students are asked to perform; for feedback, we examine the revision work requested and the rhetorical strategies used to communicate it. We evaluate direct prompting, two diversity prompting methods, and post-training. Across both tasks, directly prompted model outputs are markedly less diverse than human-authored content--78% higher on lexical (Self-BLEU) and 51% higher on semantic (embedding) similarity--and represent a narrower range of instructional forms. Diversity prompting and post-training increase variation largely through surface features without broadening the instructional repertoire. Models inherit and amplify the most normative routines of human instruction. Overcoming mode collapse in education will require richer instructional data and investment in teachers' creative capacity and professional judgment.

The Definitive Fine-Tuning Guide for 3D Generation Models

This blog post provides scripts and Docker containers for fine-tuning TRELLIS.2, a 3D generation model, using LoRA adapters on footwear data from the Google Scanned Objects (GSO) dataset. The approach focuses on improving geometric accuracy by training only the sparse-structure and shape flow diffusion transformers while freezing the texture stage. The process includes preprocessing with Blender to generate 16 views per object, converting meshes into latents, and training with Hugging Face Jobs or local Docker. Results show significant improvements in F-score, chamfer distance, and normal consistency on held-out test objects, demonstrating effective adaptation for specific 3D object categories.

Your Experts Have Partners. There's HOPE for Keeping Them Together

HOPE, a second-order expert pruning method for Mixture-of-Experts (MoE) language models, accounts for pairwise expert interactions by optimizing a quadratic program based on an interaction matrix derived from calibration data. Unlike first-order methods that prune experts independently, HOPE preserves cooperative expert groups, leading to better performance—especially at high pruning rates like 50%. On benchmarks such as SWE-Bench Pro, HOPE outperforms state-of-the-art first-order methods like REAP by up to +6.1%, maintaining model quality while significantly reducing memory footprint. The method requires only a single calibration pass and efficient quadratic programming, with negligible overhead. It has been validated on Qwen3.5 and GLM-4.5 models, showing consistent improvements across diverse tasks and calibration sets.

New NVIDIA Cosmos 3 Open Models for Interactive World Simulation

NVIDIA has introduced four new open-weight checkpoints for its Cosmos 3 model family—Cosmos3-Nano-Transfer-Auto, Cosmos3-Nano-Sim-Auto, Cosmos3-Nano-Sim-Transfer, and Cosmos3-Nano-Sim-Bimanual—enabling interactive world simulation and multi-sensor, multi-view driving scene generation. Each model is a post-trained variant of Cosmos 3 Nano with 16B trainable parameters and is based on OpenMDW1.1, allowing commercial and non-commercial use. The checkpoints support applications in robotics and autonomous driving by generating synchronized camera and LiDAR data, enabling streaming simulations, translating simulator controls into photorealistic video, and predicting visual outcomes from robot actions. They are designed to be adapted using custom data and training recipes, with support for offline data generation, causal distillation, and interactive rollouts. Resources include technical reports, demos, and notebooks for inference and adaptation.

A Closer Look at Phonon TTS. Launching High-Quality On-Device Speech That Tops the Benchmarks.

Phonon, a small text-to-speech model that runs entirely on the user's device without requiring internet access, has been released with support for English, French, German, Spanish, and Portuguese. Built on the Pocket TTS lineage using flow matching, Phonon achieves high-quality audio in compact sizes (65 MB and 75 MB), with the 31m version licensed under Apache 2.0 for commercial use. It excels in intelligibility and speed, ranking first in German and Spanish on Hugging Face's Open TTS Leaderboard and leading in CPU streaming benchmarks. The model supports voice cloning, custom voices via Gradium Studio, and integrates with Hugging Face Transformers. It is available in multiple formats and backends, including WebAssembly, GPU, and NPU, enabling deployment across phones, laptops, single-board computers, and browsers. Over 200,000 downloads were recorded in its first two weeks, with active developer adoption through tools like ExecuTorch, Micdrop, and Spaces. Future developments include support for additional languages, smaller models, and custom vocabulary fine-tuning.

Dharma Field Extractor: Any Document In, Structured Fields in JSON Out

The Dharma Field Extractor, a 2-billion-parameter model, specializes in extracting specific fields from diverse document types—such as invoices, IDs, and medical forms—into structured JSON format. It outperforms general-purpose frontier LLMs in accuracy and reduces cost by up to 147 times when self-hosted, demonstrating that domain-specialized small models can surpass large general-purpose models on well-defined tasks. The model supports both open extraction (detecting fields without a schema) and schema-directed extraction (returning exact field names and types), with training data spanning English, Brazilian Portuguese, and multilingual documents. Benchmarks show superior F1 scores and valid JSON output across real-world datasets like SROIE and FUNSD, reinforcing the thesis that specialization beats scale for enterprise document processing.

3, 7, 14, 17, 42: Instruction Tuning Installs and Sharpens Number-Choice Heuristics in Language Models

arXiv:2610.36178v1 Announce Type: new Abstract: We measure, without sampling error, the probability a language model assigns to each integer from 1 to N when asked for a random number. For a fixed prompt the model defines one probability vector, which we compute by summing over each integer's scored spellings rather than estimate by sampling, removing the noise that limits earlier studies [1, 4]. We evaluate 18 open-weight model lines at five ranges up to N = 100, under 29 decoding configurations, on two inference stacks; 15 of them have matched base and instruction-tuned checkpoints that both give usable answers. Instruction tuning makes the distribution less uniform in all 15 pairs. It installs one heuristic, round-number avoidance, and sharpens another, endpoint avoidance. Base checkpoi

Timeline and related coverage

$\Psi$-0.6: Adaptive Streams of Thought in a Unified Vision-Language World Model

arXiv:2610.32177v1 Announce Type: new Abstract: Humans reason about the physical world by flexibly combining different forms of inference as a problem unfolds. Achieving this flexibility is a major open challenge in AI: capabilities often remain separated across specialized models, limiting how they can be composed and jointly adapted to a task. We introduce $\Psi$-0.6, a unified vision-language world model that adaptively composes perception, language, geometry, and simulation within a shared reasoning process we call streams of thought. These streams interleave images, text, and explicit representations of geometry and motion, all of which the model can generate and interpret through a shared token interface. $\Psi$-0.6 surpasses leading open-weight models zero-shot on multi-view spatial

Timeline and related coverage