Discover the Best AI Resources

LTX‑2.3 IC‑LoRA — 3D render to Photoreal

Converts low‑poly 3D viewport or game/CG renders into photorealistic cinematic video while preserving the input's composition, camera motion and layout; offers Light and Strong LoRA variants to trade fidelity for aggressive photorealism.

PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception

Provides a rubric-based benchmark that converts dense image captions into instance-specific atomic checks (Must-Right and Easy-Wrong) and a gated scoring rule, aiming to expose perceptual brittleness and better align multimodal model evaluation with human judgment.

fal · Krea 2 Style LoRAs

Provides 1,503 Krea 2 style LoRAs (original safetensors + ComfyUI builds) trained on fal.ai, each with a short trigger phrase and downloadable weights for quick style transfer or further retraining.

DeepSeek-V4-Pro-DSpark

Mixture-of-Experts LLM designed for million-token contexts, combining hybrid compressed attention, FP4/FP8 quantization-aware training for MoE experts, and multi-mode 'thinking' (Non-think/Think High/Think Max); includes a speculative-decoding extension for faster inference.

DeepSeek-V4-Flash-DSpark

A Hugging Face model checkpoint that attaches a speculative decoding module to DeepSeek-V4-Flash, enabling million-token context handling with MoE architecture, FP4/FP8 mixed precision, and long-context inference optimizations.

Vāgdhenu — Sanskrit Chant Corpus

Provides ~1,467 single-speaker Sanskrit chant audio clips (≈5.3 hours) with aligned transcripts and prosodic metadata for meter-aware TTS training. Two recording/config styles (style_a/style_b), 24 kHz mono WAVs, metadata includes Devanagari, SLP1, Kannada text, meter, duration, session/take. CC-BY-4.0.

Rampart

Detects and redacts personally identifiable information (PII) in user-typed text on-device, replacing sensitive values with stable placeholders before any data leaves the browser. Uses a small quantized ONNX token-classification model plus deterministic recognizers for structured identifiers, and applies a policy-driven keep-set for coarse geography.

The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning

Proposes Monotonic Inference Policy Improvement (MIPI) and a two-step Monotonic Inference Policy Update (MIPU) to address training–inference probability mismatch in LLM reinforcement learning by constructing sampler-referenced candidate updates and accepting synchronized updates using an inference-gap proxy; shows improved reasoning accuracy and stability under FP8-quantized rollouts.

Huihui-GLM-5.2-abliterated-GGUF

An uncensored GGUF build of GLM-5.2 that applies weight “abliteration” to remove refusal filters and produce a locally runnable text-generation model; includes quantization conversions and shard-merge instructions, intended for experimental research rather than production use.

Metacognition-Bench

Provides 300 adversarial "metacognitive-trap" problems to measure whether LLMs notice and recover from their own reasoning errors. Combines multiple-choice vulnerability tests with free-form adapter-gain evaluation and ships per-model metacognition adapters for frozen-base probing.

Morphing into Hybrid Attention Models

Treats hybrid layer selection as a budget-constrained subset optimization and introduces FlashMorph: a pipeline that equips each transformer layer with a linear-attention branch, jointly optimizes layerwise gates on synthetic long-context retrieval data, then discretizes, distills, and finetunes—achieving strong long-context recall using only 20M selection tokens.

Sun Direction LoRA (Flux2Klein 9B)

Applies or repositions directional sunlight in outdoor images by using a LoRA trained for Flux2Klein 9B to match a reference sun elevation and rotation. Workflow uses an overcast intermediate and a sphere (ball) reference; includes a ComfyUI node and Blender scene for rendering the reference.