Discover the Best AI Resources

Agents-A1: Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

Provides quantized GGUF weights and configs for Agents‑A1 — a 35B Mixture-of-Experts agent trained for long-horizon, tool-enabled reasoning; supports 262K-context serving and runtimes like vLLM and SGLang.

MemSyco-Bench: Benchmarking Sycophancy in Agent Memory

Evaluates how long-term memory in LLM agents amplifies sycophantic behavior and when memory should or should not influence decisions. Provides five targeted tasks, 1,550 standardized samples, an evaluation pipeline, and baseline adapters to test memory use, conflicts, scope, updates, and personalization.

Explorer_LLM_Rec_Competition

Provides anonymized multi-domain user behavior sequences and content metadata (short video, ads, e-commerce, live) for cross-domain recommendation, semantic-ID mapping, and content-understanding tasks. Key tables include per-user multi-domain behavior (~500k rows), pid→three-segment semantic IDs, captions, and level-3 tags; all item IDs are hashed for privacy.

Giga-World-1

Diffusion-based generative model for scene and video synthesis, providing full Diffusers checkpoints and scene LoRA for fast adaptation. Includes Stage‑1 nano (1.3B) and pro (5B) variants and modular transformer/VAE components.

Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts

Adapts pretrained Vision-Language-Action (VLA) models to new camera poses and robot embodiments from a single demonstration by performing weight-vector arithmetic that injects domain-specific information. Filters noise via subspace alignment of singular components; designed for one-shot adaptation under visual and embodiment shifts.

Leanstral 1.5 119B A6B

A code-agent model for Lean 4 that automates repository-level formal proofs and verification; a Mixture-of-Experts architecture (119B total, 6.5B active) with 256k context, multimodal input and an Apache-2.0 license.

colibri

Streams routed experts from disk and treats storage, RAM and VRAM as a single inference hierarchy so MoE models (hundreds of billions to trillions of parameters) can run on consumer or heterogeneous hardware; single-file C engines with zero runtime deps and optional Vulkan/CUDA/Metal backends, speed governed by placement and disk I/O.

ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving

Predicts per-request MoE expert footprints from prefill activations and routes decode requests to workers that maximize expert-locality, lowering decode latency by combining offline K-means partitioning with online locality-band routing and a KV-block–coindexed signature cache.

EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments

Provides a benchmark and protocol to evaluate agents that iteratively edit executable policies under a fixed interaction budget, recording full execution–feedback–revise trajectories. Built from compact RL environments with trajectory-level diagnostics and hidden held-out validation.

Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling

Accelerates text-to-image diffusion for pretrained flow-matching models using a staged low-to-high-resolution pipeline: fast low-res sampling, pixel-space GAN super-resolution, light latent noising, and short high-res refinement — >10× end-to-end speedups without retraining.

Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots

Provides a portable C++ inference runtime to deploy embodied AI models (vision–language–action and world–action) on heterogeneous robot hardware, enabling latency-first batch-1 closed-loop control. Key features include modular multi-rate layers, fused low-latency inference, and extensible head/IO plugins.

GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluation

Provides a systematic benchmark and design roadmap for video-based world models to evaluate robot policies, introducing WMBench and GigaWorld-1 optimized for long-horizon, action-faithful rollouts. Offers controlled comparisons across model families, action encodings, and 324k+ simulated vs real rollouts, with code, models, and datasets released for reproducible evaluation.