Research Papers Rankings
The overall board: every AI paper from the last 90 days, across language models, agents, vision, robotics and the rest. Ranked by three independent signals — GitHub star velocity on the official implementation, citation count, and Hugging Face attention — so a paper that only trended for a day does not hold a place. Rebuilt every day.
Kimi K3 is an open Mixture-of-Experts model with 2.8T parameters (104B activated per token), native vision input and a 1-million-token context window, built on Kimi Delta Attention and post-trained with reinforcement learning across general, agentic and coding tasks.
LingBot-World 2.0 upgrades the game world model to an unbounded interaction horizon with consistent output quality via a causal pretraining paradigm, distills a real-time variant fast enough to drive 720p video at 60 fps, and greatly expands the action set (attacking, archery, spell-casting, shooting) plus text-driven interactive elements.
FreeToken rethinks local inference around two realities of edge AI: agent workloads keep changing shape, and every machine's resource balance differs. It co-designs model layout, expert residency, CPU-GPU execution and memory management instead of committing to a fixed offloading strategy.
Prime Agent is an open harness for long-horizon coding agents built on the Recursive Language Model idea: a persistent IPython session does test-time computation, while histories, memories, skills and subagent specs carry over between runs.
VoiceMem gives duplex speech models a working memory that keeps facts and emotional context across a conversation, so a voice assistant can remember both what you said and how you said it, in real time.
LLM-as-a-Verifier turns a language model into a verifier by computing expectations over its scoring-token logits instead of prompting for discrete judgments, yielding continuous feedback with no extra training. The authors report state-of-the-art results on benchmarks including Terminal-Bench V2 and SWE-Bench Verified, and ship a Claude Code extension that watches agents and supplies dense rewards for RL.
Inspired by human working memory while copying, this technical report builds an end-to-end OCR model whose decoding cost stays flat as output text grows long, avoiding the KV-cache slowdown and memory creep of LLM-decoder OCR systems.
Xiaomi's robotics team presents a vision-language-action foundation model for mobile manipulation, pretrained on more than 100K hours of real-world UMI trajectories with auto-labeled scene-transition language, then post-trained to match embodiments and human imperative prompts. The paper claims clean scaling with more data and parameters, out-of-the-box performance in unseen environments and efficient fine-tuning for dexterous tasks.
Alaya-EVOKE externalizes persistent scene geometry into a camera-indexed world state bank so the denoiser context stays bounded, and trains with a sparse-attention teacher that supervises long horizons at linear cost, exposing content drift and supporting prompt changes mid-sequence. The teacher distills into a three-step student that the authors report producing each 1.5-second chunk in 2.11s on a single H200 GPU.
Apodex 1.1 targets what the authors call working capability: it scales up the diversity and verifiability of executable file, search and code environments, while training agents to decompose long-horizon tasks, delegate parallel work and integrate asynchronous results.
This technical report upgrades LingBot-VLA with a revamped data pipeline of about 60,000 pretraining hours: 50K robot-trajectory hours across 20 embodiments plus 10K egocentric human-video hours. It extends control beyond dual arms to heads, waists, mobile bases and dexterous hands, aiming squarely at the gap between lab robotics and real deployment.
AuK unifies speech generation and editing in a single open-source model: you describe the desired change in natural language, and it either synthesizes new speech or modifies existing audio accordingly.
BDH-CQ keeps a recurrent memory continuously updated by the input and solves queries through iterative computation in a high-dimensional latent space, without verbalizing intermediate reasoning; the authors report 29.5% pass@2 on the ARC-AGI-1 evaluation set at about $0.0007 of inference cost per task.
ABot-World-0 is an action-conditioned video world model trained on multi-source data from AAA games, simulation engines and internet videos, controlled through raw keyboard input with reference-character memory for consistent third-person rollouts. The authors report streaming 720p at up to 16 FPS on one RTX 5090 with 1.2s action-to-first-frame latency, targeting real-time long-horizon closed-loop interaction.
OSWorld 2.0 from the xlang-ai team replaces short scripted tasks with 108 long-horizon computer-use workflows built on authentic artifacts and stateful user profiles; humans take a median of about 1.6 hours per task. The headline finding is how far agents still are: the best model, Claude Opus 4.8, completes only 20.6% of tasks, often losing track of constraints or skipping verification.
WeMM-Embedding is a family of universal multimodal embedding models (2B, 4B and 9B) covering text, images, video, visual documents and arbitrarily interleaved inputs, with flexible output dimensions, trained by large-scale alignment followed by refinement with curated relevance supervision.
AutoResearch connects idea generation with idea execution: candidate ideas are formed by integrating fresh research signals with accumulated domain knowledge and cross-reviewed by multiple models, then coordinated agents decompose the plans and establish them through actual experimentation.
This survey decomposes a self-improving agent into a foundation model and an operational scaffold of prompts, memory, tools and control logic, then defines improvement as a self-induced update operator that converts experience into accumulated capability with minimal human input. It organizes the growing literature by update target and driving signal, from prompt and memory edits to weight-level self-modification.
DreamX-World 1.0 is a general-purpose interactive world model that turns text or image prompts into steerable video: you can move the camera, revisit earlier regions, and trigger promptable events across photorealistic, game-style and stylized scenes. The authors report a few-step autoregressive design distilled for speed, running at up to 16 FPS on eight RTX 5090 GPUs.
Frontis-MA1 ships with OpenMLE, an open full-stack system (task gyms, RL operator learning, evolutionary search) for studying recursive self-improvement. Its 35B meta-evolution agent, post-trained around Draft, Improve, Debug and Crossover program-evolution operators, claims MLE-Bench Lite results the authors say exceed GPT-5.5 plus Codex, with components transferring to held-out NatureBench Lite.
The overall board: every AI paper from the last 90 days, across language models, agents, vision, robotics and the rest. Ranked by three independent signals — GitHub star velocity on the official implementation, citation count, and Hugging Face attention — so a paper that only trended for a day does not hold a place. Rebuilt every day.
A dash means the signal was unavailable, not zero.