AI Model2026
A GGUF-quantized, locally runnable build of Gemma 4 12B Unified (image-text-to-text) packaged by unsloth; preserves multimodal (image/audio) input support under an Apache-2.0 license and is compatible with common GGUF runtimes and Unsloth Studio.
AI Agent Papers2026
Automates distillation of heterogeneous traces from a target person or role into versioned, inspectable skill packages for LLM agents — producing separate capability and bounded-behavior tracks that support natural-language corrections, rollback, and cross-host installation. Ships with an open system and a skills gallery.
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.
AI Dataset2026
Provides 462 unrestricted long-form chain-of-thought reasoning traces distilled from the full Mythos V2 model (≈104.7M characters); intended for long-context evaluation, trace analysis and process-level supervision. License unknown—verify before reuse.
Proposes TrOPD, a method that restricts token-level on-policy distillation to regions where teacher supervision is reliable to stabilize training under teacher–student distribution mismatch. Adds outlier handling (clipping, masking, forward-KL) and off-policy guidance; shows consistent gains on math reasoning, code generation and general benchmarks.
Studies small trainable adapters (PEFT) used as persistent personal models on top of large foundation models, analyzing three scaling axes—Scale Up, Scale Down, Scale Out—and introducing MinT, an infrastructure for adapter identity, provenance, evaluation, and serving.
AI Agent Papers2026
Localizes harmful span-level errors inside long research-agent trajectories to show which trajectory segments make final answers unreliable. Provides a 1,000-instance TELBench of annotated spans and DRIFT, a claim-centric auditing method that improves span-level localization and first-error accuracy by up to 30 percentage points.
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.
Evaluates multimodal LLMs on streaming egocentric video for spatial intelligence using 1,680 human-annotated questions across 348 videos; organizes tasks into four hierarchical levels (perception → tracking → simulation → allocentric mapping) and highlights allocentric mapping as the main bottleneck.
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.
Learns fine-grained preferences over sub-trajectories to identify and penalize redundant steps in long chain-of-thoughts, letting models "fold" reasoning chains into concise paths; reports ~56% token reduction on DeepSeek-R1-Distill-Qwen-7B while keeping accuracy.
AI Agent Papers2026
Enables agents to proactively discover multiple hidden problems in a user context and pair each with supporting evidence and concrete actions. Uses iterative discovery (batch rounds conditioned on prior finds) and reusable "thought templates" to expand coverage and ground claims.