The Price of Anarchy in Disaggregated Inference
Disaggregated inference architectures physically separate prefill and decode phases onto distinct GPU pools, creating competing "agents" that share a fixed hardware budget. We prov...
Research Papers
Latest AI/ML research from ArXiv and Papers with Code
OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data
Cloning camera motion from reference videos is an important task in video generation, as videos provide intuitive and precise control. Existing methods either directly use parametr...
Avatar V: Scaling Video-Reference Avatar Video Generation
Generating avatar videos that are not merely visually similar to a target individual but behaviorally recognizable, faithfully reproducing their talking rhythm, gestural tendencies...
μ_0: A Scalable 3D Interaction-Trace World Model
World models that capture how actions induce physical change enable scalable robot learning without reliance on embodiment-specific action labels. Pixel-space video models provide ...
Self-Evolving Visual Questioner
Vision-language models (VLMs) are typically trained as passive answerers, while their ability to actively ask diverse, non-trivial, visual-centric and grounded questions remains un...
ArogyaSutra: A Multi-Agent Framework for Multimodal Medical Reasoning in Indic Languages
Multimodal Large Language Models (MLLMs) have shown promising reasoning capabilities in general domains, yet their performance remains limited in specialized settings such as healt...
HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers
Holistic visual tokenizers are fundamental to unified multimodal models (UMMs) as they map diverse visual inputs into a unified representation space. In this paper, we present HYDR...
EvoBrowseComp: Benchmarking Search Agents on Evolving Knowledge
Search Agents -- large language models augmented with search tools -- have intensified the need for future-proof evaluation benchmarks. Existing benchmarks such as BrowseComp rely ...
EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments
Large language model (LLM) agents have achieved strong performance on a wide range of benchmarks, yet most evaluations assume static environments. In contrast, real-world deploymen...
Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning
Latent chain-of-thought compresses reasoning by replacing visible reasoning traces with continuous hidden-state recurrence, but existing formulations are difficult to optimize with...
See What I See, Know What I Think: Dense Latent Communication Across Heterogeneous Agents
Multi-agent systems communicate mostly through text, paying a lossy and expensive decode and re-encode cost. KV-cache communication is a promising alternative, yet most prior work ...
Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents
Interactive LLM agents are becoming part of daily work, but they do not reliably become easier to work with over time: a correction remembered in one session may still be violated ...
Rethinking RAG in Long Videos: What to Retrieve and How to Use It?
Retrieval-augmented generation is moving beyond text into long, egocentric video, where systems must select query-relevant chunks across multiple modalities and temporal granularit...
HiLo-Token: Input-Adaptive High-Low Frequency Token Compression for Efficient Image Editing
Creative image editing tools, such as Photoshop's Remove or Generative Fill buttons, are central to everyday customer use and account for a major share of traffic in Photoshop and ...
RepWAM: World Action Modeling with Representation Visual-Action Tokenizers
This work presents RepWAM, a representation-centric world action model (WAM) built on representation visual-action tokenizers. Existing WAMs typically inherit reconstruction-orient...
Aligning Quantum Operators with Large Language Models
Can Large Language Models (LLMs) understand and reason about quantum operators? Despite their remarkable capabilities in mathematics and symbolic reasoning, LLMs remain inherently ...
LingxiDiagBench: A Multi-Agent Framework for Benchmarking LLMs in Chinese Psychiatric Consultation and Diagnosis
Mental disorders are highly prevalent worldwide, but the shortage of psychiatrists and the inherent subjectivity of interview-based diagnosis create substantial barriers to timely ...
A Benchmark and Framework for Evaluating Next Action Predictions in Spreadsheets
Predictive code completion greatly accelerates how quickly developers work. In spreadsheets, despite being much more common, such auto-completion features are virtually non-existen...
The Hidden Power of Scaling Factor in LoRA Optimization
In Low-Rank Adaptation (LoRA), the scaling factor α is often treated as a mere complement to the learning rate, yet its role in optimization remains poorly understood. In this pape...
Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation
On-policy distillation (OPD) has recently become a prominent post-training recipe as it combines two desirable ingredients: on-policy student trajectories and dense teacher supervi...
APPO: Agentic Procedural Policy Optimization
Recent advances in agentic Reinforcement Learning (RL) have substantially improved the multi-turn tool-use capabilities of large language model agents. However, most existing metho...
On Subquadratic Architectures: From Applications to Principles
Transformers dominate modern sequence modeling, but their quadratic attention incurs substantial computational cost. Subquadratic architectures offer a scalable alternative. Howeve...
Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training
There are two main Parameter-Efficient Fine-Tuning (PEFT) techniques for Large Language Models (LLMs). While Low-Rank Adaptation (LoRA) introduces additional weights between the LL...
Quickest Detection of Hallucination Onset: Delay Bounds and Learned CUSUM Statistics
Token-level hallucination detectors are evaluated as classifiers, by AUC over all tokens, yet a streaming monitor is judged by its reaction time: the number of tokens that pass bet...