A pretrain-then-transfer method for streaming recommendation that decouples refreshable behavioral knowledge from task-specific geometry to enable continual model refresh without downstream interference; introduces Behavioral Multi-Token Prediction and Anchored Calibration Residual and shows 4–12% offline gains plus live Shopee A/B lifts.
AI Agent Papers2026
Analyzes how to build effective training environment distributions for multimodal agents and proposes Ability-aware Environment Selection (AES) and Hierarchical Difficulty Curriculum (HDC) to improve diversity and difficulty scheduling, yielding large relative gains in experiments.
Systematically studies how language and vision interact during unified multimodal pretraining, identifies mechanisms that enable modality synergy versus competition, demonstrates the benefit of early joint training, and derives efficient pretraining recipes validated at scale.
AI Video2026
Provides ComfyUI-compatible pruned/curve-form LoRA conversions of the MiniMax‑H3 Turbo 4-step audio‑video generation preview, including further-trained ckpt500 EMA and non‑EMA variants and an example ComfyUI workflow for low-step experiments.
AI Dataset2026
Provides per-decision training samples for RL-driven command-line LLM agents: each record pairs a task prompt plus terminal history with a teacher's next-action in Terminus-2 JSON. Around 31k verifier-passing samples from 630 ATCB tasks, formatted for NeMo Gym's terminus_judge and licensed CC-BY-4.0.
AI Dataset2026
Provides ~39 TB of pre‑beamformed (channel capture) ultrasound RF data and metadata in zea/HDF5 format for reconstruction, flow, and inverse‑problem tasks. Released under CC‑BY‑4.0 and curated for training and evaluating ultrasound/RF foundation models.
Turns adapter placement for PEFT on YOLO-family real-time detectors into an auditable constraint-planning problem that emits budgeted target-module plans or calibrated refusals; shows planner-selected RS-LoRA improves mAP and cuts peak training memory in evaluated detectors.
AI Video2026
A LoRA adapter for MiniMax H3 that improves photorealistic rendering of people—preserving skin texture, coherent micro-expressions, film-style lighting and subtle handheld motion. Trigger word: r34l1sm; intended for text-to-video portrait and close-up shots.
AI Model2026
A 2.9B-parameter text-to-image model fine-tuned from CircleStone Labs' Anima for anime and illustration; trained on an additional 1.7M samples with a July 2026 knowledge cutoff. Designed for non-commercial creative image generation and ComfyUI integration; weights released under the CircleStone Labs Non-Commercial (derivative) license.
AI Dataset2026
Provides an L1 filtered English web corpus from recent Common Crawl snapshots for LLM pretraining, including main-text extraction, language and heuristic filtering, sensitive-field replacement, customized cleaning, and MinHash deduplication; contains 1T+ tokens across ~1.14B documents with structured metadata fields.
AI Agent Papers2026
Trains compact conversational agents to adapt at runtime to changing 'Harness' configurations (Skills, Hooks, prompts, tools) using Harness-Aware Training (HAT): Harness-State Augmentation, on-policy distillation, and RL to preserve generality while meeting low-latency deployment constraints.
AI Model2026
Post-trained Qwen3.8-27B variant using the COLD FUSION (GAIN+Unsloth) tuning to reduce internal reasoning-token use and improve instruction following while keeping base capabilities. Deliverables include 256k-context-compatible GGUF quants (regular and MTP, NEO IMATRIX), vision support via an mmproj, and three reasoning-effort modes (xhigh/medium/low).