AI Model2026
A GGUF-format 9B model derived from Qwen3.5, fine-tuned for agentic coding, tool-calling, reasoning and vision-capable multimodal prompts. Optimized for local 8‑bit inference on 16GB-class machines; community experimental release for research use.
AI Model2026
A GGUF-format 9B LLM fine-tuned for code generation and agentic tool-calling that uses Multi-Token Prediction (MTP) and draft heads to increase throughput and long-range planning. Intended for local inference and research/experimental coding workflows; Apache‑2.0 license.
AI Dataset2026
Supervised fine-tuning dataset of instruction-style examples in English and Chinese covering generation, QA, reasoning, math and code — targeted for SFT of 10–100B-parameter LLMs. Associated with arXiv:2602.09003; first published May 21, 2026.
AI Dataset2026
Provides 100,000 generated low-quality↔high-quality image pairs created with modern multi-frame/multi-modal models to boost generalization of image restoration methods; includes train/test JSONL lists, baseline training code, and pretrained checkpoints under CC BY‑NC‑ND 4.0.
AI Model2026
A 1.08B-parameter causal LLM engineered for on-device text generation with native long-context (131k tokens) and built-in Think/No-Think modes. It emphasizes tool-calling support, lightweight deployment formats (BF16, GGUF, MLX), and RL+OPD post-training for stronger reasoning and code generation.
Analyzes spatial representations in vision–language models and reveals a consistent vertical-position ↔ distance entanglement; introduces SpatialTunnel, a synthetic benchmark that exposes this perspective-driven shortcut, and provides code and a project page.
AI Dataset2026
Metadata-only corpus of 146.3M new GitHub source-code files (commit_id, rel_path, language) intended as an incremental update to Nemotron v1/v2 for LLM code pretraining; CC-BY-4.0 licensed and designed to be used jointly with older versions.
AI Agent Papers2026
Analyzes when masking stale observations improves long-horizon search agents and why, identifying an asymmetric inverted-U relationship between masking benefit, retriever quality, and model capacity; explains a token-for-turn trade-off and releases evaluation scaffolds and trajectories.
Uses search-agent reading traces and tiered distractors to train LLMs for long-context, multi-hop reasoning, and introduces a rubric reward that supervises entity-level steps (applied only to correct finals). Improves evidence-grounded reasoning and resists reward hacking across 4B–30B models.
Analyzes how single-domain RL fine-tuning on LLMs induces cross-domain interference and shows this damage concentrates in a low-dimensional shared conflict subspace; proposes a local perturbation theory and short domain "refresh" procedures that selectively recover earlier domains with minimal collateral loss.
Studies when and how to combine visual future rollouts from world models with abstract reasoning in multimodal LLMs. Proposes PF-OPSD — a teacher-student distillation that uses ground-truth future videos during training — and evaluates on two human-verified benchmarks, improving accuracy ≈10% while improving robustness to noisy rollouts.
AI Dataset2026
Generates synthetic coding-agent session traces by pairing remotely hosted open agent models with local llama.cpp user models across real open-source codebases. Each trace records read/write/edit/bash actions and tool use; the dataset is a reproducible cartesian product (20×3×20×20 = 24,000 sessions) under an MIT license.