Uses pretrained multimodal LLMs as zero-shot, training-free reward models for text-to-image RL by scoring how well the original text prompt can be recovered from a generated image via image-conditioned prompt log-likelihood; includes a Self-SpectraReward closed-loop variant.
AI Agent Papers2026
Acquires repository knowledge via a targeted QA loop before generating patches, decoupling knowledge acquisition from repair. A Questioner and Answerer produce evidence-grounded QA pairs that a Resolver uses to generate fixes; improves Pass@1 on SWE-bench Verified with modest overhead.
Builds structured knowledge graphs for retrieval-augmented generation via a multi-step GraphRAG pipeline that separates extraction from consolidation. Key features include typed two-stage extraction, DBSCAN-backed deduplication, LLM summarization, Leiden community detection, and a compact 7B extractor model (Meno-Lite-0.1).
AI Video Papers2026
Comprehensive benchmark and automated evaluation framework for keyframe-conditioned video generation—decomposes keyframe execution into six metrics and assesses overall video quality with evidence-grounded MLLM judgments and specialized perception models.
Specialized LLM for clinical workflows trained via a human-gated self-evolution loop to improve patient consultation, multimodal clinical reasoning, interactive diagnosis, and EHR tool use. Iteratively refines targeted synthetic and curated data based on benchmark failures to raise specific capabilities without broad regressions.
AI Agent Papers2026
Converts completed on-policy trajectories into natural-language 'hindsight skills' and converts the skill-induced action probability shifts into a dense token-level on-policy distillation signal, jointly optimized with outcome-based RL to improve sample efficiency and long-horizon agent behavior.
AI Video Papers2026
Enables efficient, generalist video understanding by combining an Inflated 3D Vision Transformer and adaptive frame-resolution streaming with a scalable video data synthesis pipeline; ships as a fully open 4B-parameter MLLM that improves general, long-form, and streaming benchmarks.
Embodied AI2026
Analyzes adversarial weaknesses of World-Action Models (WAMs) via BadWAM, a framework that crafts visual perturbations to decouple a model’s imagined future from its executed actions. Introduces two attack modes—action-only (disruptive) and imagination-preserving (stealthy)—and shows large drops in closed-loop task success (e.g., 96.5%→43.1%).
AI Agent Papers2026
Turns fragile, implicit search progress into explicit, persistent, shared state for multi-agent information seeking — externalizes progress as Frontier Task, Evidence Graph, Coverage Map and Failure Memory, and uses pipeline-parallel scheduling plus a middleware harness to avoid repeated failed searches and improve utilization and throughput.
Expands a Transformer’s residual stream into many parallel streams and introduces xHC to scale Hyper-Connections beyond N=4. Combines temporal feature augmentation with sparse residual updates (update k=4 of N=16) and xHC-Flash memory optimizations to raise downstream scores while cutting effective compute and memory traffic.
AI Agent Papers2026
A vision-language-action foundation model trained on 100k+ hours of real-world robot manipulation trajectories to follow natural-language instructions and adapt to downstream tasks with minimal fine-tuning. Uses a two-stage (pre-/post-) training recipe and a scalable auto-labeling pipeline; shows clear scaling benefits and state-of-the-art sim-to-real transfer on standard benchmarks.
AI Video Papers2026
Evaluates whether video models reason according to physical laws by treating generated videos as visible reasoning traces and using a three-stage Perception–Formulation–Deduction protocol. Includes Orchard (400 mechanics videos), chain-of-frames prompting on annotated first frames, and a hybrid MLLM-plus-objective scoring suite for stage-resolved diagnostics.