From Pixels to Words -- Towards Native One-Vision Models at Scale
Current vision-language models (VLMs) typically stitch together separate image encoders and language decoders via multi-stage alignment, a modular framework that inevitably fragmen...
Research Papers
Latest AI/ML research from ArXiv and Papers with Code
ResearchMath-14K: Scaling Research-Level Mathematics via Agents
The frontier of mathematics is defined by problems whose solutions are not yet known, yet it remains unclear whether language models can meaningfully engage with such problems with...
Same Question, Different Source, Different Answer: Auditing Source-Dependence in Medical Multi-Source RAG
A retrieval-augmented generation (RAG) system deployed over a multi-author institutional corpus can give a different answer to the same question depending on which source it retrie...
The Chain Holds, the Answer Folds: Trace-Answer Dissociation in Reasoning Models Under Adversarial Pressure
Reasoning models are evaluated on single-turn benchmarks but deployed in multi-turn dialogue, where users push back on correct answers. Under sustained adversarial pressure we find...
Show, Don't TELL: Explainable AI-Generated Text Detection
Research on AI-generated text detection has presented a number of approaches to discern human from AI prose, some of which achieving high in-distribution performance. However, real...
Category-Level 3D Correspondence in Camera Space via Morphable Object Priors
Understanding 3D objects from images is fundamental to robotics and AR/VR applications. While recent work has made progress in category-level pose estimation, current representatio...
AI, Take the Wheel: What Drives Delegation and Trust in Human-Computer Cooperative Question Answering?
AI systems are fallible, and humans can make mistakes in deciding whether to trust AI over their own judgment. Thus, improving human-AI collaboration requires understanding when, w...
AgensFlow: A Coordination-Policy Substrate for Multi-Agent Systems
Multi-agent systems built on large language models (LLMs) require many coordination choices that are difficult to fix a priori: which skill protocol to invoke, which agent role sho...
MERIT: Learning Disentangled Music Representations for Audio Similarity
Current music similarity models typically compute a single, monolithic score, entangling distinct musical dimensions like melody, rhythm, and timbre. This limits user control and i...
Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini
We introduce Gemini Embedding 2, a native multimodal embedding model that allows embedding video, audio, image, and text modalities in a unified representation space. We leverage t...
PANDO: Efficient Multimodal AI Agents via Online Skill Distillation
Recent advances in multimodal web agents often rely on increased inference-time computation, including rollout search, verifier passes, offline skill discovery, and specialist mode...
Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation
On-policy distillation (OPD) trains a student on its own rollouts with token-level teacher supervision. Recent selective OPD methods exploit the non-uniformity of OPD signals by pr...
QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents
Social deduction games have become a popular testbed for probing reasoning, deception, coordination, and belief modeling in Large Language Model (LLM) agents. However, most environ...
PEAM: Parametric Embodied Agent Memory through Contrastive Internalization of Experience in Minecraft
We present PEAM, a Parametric Embodied Agent Memory framework in Minecraft that transforms agent memory from inference-time retrieval into parameter-resident skills internalized th...
Verus-SpecGym: An Agentic Environment for Evaluating Specification Autoformalization
AI coding agents are increasingly used to write real-world software, but ensuring that their outputs are correct remains a fundamental challenge. Formal verification offers a promi...
GE-Sim 2.0: A Roadmap Towards Comprehensive Closed-loop Video World Simulators for Robotic Manipulation
We introduce GE-Sim 2.0 (Genie Envisioner World Simulator 2.0), a closed-loop video world simulator for robotic manipulation. Building on the action-conditioned video generation fr...
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
Vision-language models (VLMs) commonly formulate visual grounding and detection as a coordinate-token generation problem, serializing each 2D box into multiple 1D tokens that are l...
MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation
Large language model (LLM) agents rely on reusable skills to solve complex tasks. However, existing skill creation approaches treat skills as isolated and static artifacts, limitin...
SpatialBench: Is Your Spatial Foundation Model an All-Round Player?
While spatial foundation models have demonstrated impressive performance on standard datasets, a critical question remains: are they truly all-round players capable of generalizing...
RT-Lynx: Putting the GEMM Sparsity In a Right Way for Diffusion Models
Diffusion Transformers (DiT) achieve strong performance in image generation but incur substantial inference costs. While prior work has reduced this cost via quantization and disti...
DEI: Diversity in Evolutionary Inference for Quality-Diversity Search
We present DEI: Diversity in Evolutionary Inference, a distributed Quality-Diversity (QD) search framework that assigns heterogeneous large language models (LLMs) as mutation opera...
Recursive Flow Matching
Generative models have emerged as a powerful paradigm for solving physics systems and modeling complex spatiotemporal dynamics. However, achieving high physical accuracy without in...
SIA: Self Improving AI with Harness & Weight Updates
Humans are the bottleneck in building and improving AI. Both the models and the agents that wrap them are written, tuned, and corrected by people. The long-horizon goal of an AI th...
SkillGrad: Optimizing Agent Skills Like Gradient Descent
Agent skills provide a lightweight way to adapt LLM agents to specialized domains by storing reusable procedural knowledge in structured files. However, whether downloaded from thi...