SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Agent skills today are hand-crafted, generated one-shot, or evolved through loosely controlled self-revision, none of which behaves like a deep-learning optimizer for the skill, an...
Research Papers
Latest AI/ML research from ArXiv and Papers with Code
PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion
Most practical high-resolution text-to-image systems, including latent diffusion and autoregressive models, perform generation in a compact latent space, and a decoder maps the gen...
CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models
Video prediction is increasingly viewed as a path toward generalizable world models, yet it remains unclear whether these systems learn underlying causal structure or merely exploi...
Contrastive Distribution Matching for Amortized Sequential Monte Carlo in Discrete Diffusion
Discrete diffusion models have emerged as powerful frameworks for generating structured categorical data. However, efficiently sampling from reward-tilted distributions remains a f...
The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation
Large language models (LLMs) have demonstrated impressive reasoning abilities across a wide range of tasks, but data contamination undermines the objective evaluation of these capa...
Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulation
Discrete diffusion models are often trained through clean-data prediction, but the prediction can be used in different ways to define the reverse dynamics. In Masked Diffusion Mode...
EMMA: Extracting Multiple physical parameters from Multimodal Data
We introduce EMMA, a physics-informed multimodal framework that recovers all identifiable dynamical parameters of a system directly from raw video, audio, and image-based time-seri...
Agentic CLEAR: Automating Multi-Level Evaluation of LLM Agents
Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing a...
VGenST-Bench: A Benchmark for Spatio-Temporal Reasoning via Active Video Synthesis
Spatio-temporal reasoning is a core capability for Multimodal Large Language Models (MLLMs) operating in the real world. As such, evaluating it precisely has become an essential ch...
DecQ: Detail-Condensing Queries for Enhanced Reconstruction and Generation in Representation Autoencoders
Representation Autoencoders (RAEs) leverage frozen vision foundation models (VFMs) as tokenizer encoders, providing robust high-level representations that facilitate fast convergen...
Live Music Diffusion Models: Efficient Fine-Tuning and Post-Training of Interactive Diffusion Music Generators
Interactive streaming music generation promises the use of generative models for live performance and co-creation that is impossible with offline models. However, SOTA models exist...
RiT: Vanilla Diffusion Transformers Suffice in Representation Space
Flow matching with x-prediction -- regressing the clean data point rather than the ambient velocity -- is known to exploit low-dimensional manifold structure effectively in pixel s...
MotiMotion: Motion-Controlled Video Generation with Visual Reasoning
Current motion-controlled image-to-video generation models rigidly follow user-provided trajectories that are often sparse, imprecise, and causally incomplete. Such reliance often ...
LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning
Joint audio-visual reasoning is essential for omnimodal understanding, yet current multimodal large language models (MLLMs) still struggle when reasoning requires fine-grained evid...
SpaceDG: Benchmarking Spatial Intelligence under Visual Degradation
Multimodal Large Language Models (MLLMs) have made rapid progress in spatial intelligence, yet existing spatial reasoning benchmarks largely assume pristine visual inputs and overl...
One Sentence, One Drama: Personalized Short-Form Drama Generation via Multi-Agent Systems
Existing approaches for digital short-drama production typically rely on one-shot LLM generated scripts and loosely coupled pipelines, which fail to satisfy three key requirements ...
Segment Anything with Motion, Geometry, and Semantic Adaptation for Complex Nonlinear Visual Object Tracking
Traditional visual object tracking (VOT) methods typically rely on task-specific supervised training, limiting their generalization to unseen objects and challenging scenarios with...
ThriftAttention: Selective Mixed Precision for Long-Context FP4 Attention
Efficient attention algorithms are critical to mitigate the quadratic cost of attention in long-context workloads. Prior work utilises block-scaled quantisation techniques on Black...
FashionLens: Toward Versatile Fashion Image Retrieval via Task-Adaptive Learning
Fashion image retrieval is a cornerstone of modern e-commerce systems. A unified framework that supports diverse query formats and search intentions is highly desired in practice. ...
The Expense of Seeing: Attaining Trustworthy Multimodal Reasoning Within the Monolithic Paradigm
The rapid proliferation of Vision-Language Models (VLMs) is often framed as enabling unified multimodal knowledge discovery but rests on an under-examined assumption: that current ...
TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation
Public transit route planning traditionally depends on structured map infrastructure and complex routing engines, and no existing dataset supports training models to bypass this de...
Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?
Multimodal Large Language Models (MLLMs) are increasingly deployed in human-facing roles where personality perception is critical, yet existing benchmarks evaluate this capability ...
Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving
Robust training and validation of Autonomous Driving Systems (ADS) require massive, diverse datasets. Proprietary data collected by Autonomous Vehicle (AV) fleets, while high-fidel...
From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning
Reinforcement learning from verifiable rewards (RLVR) has shown strong promise for LLM reasoning, but outcome-based RLVR remains inefficient on hard problems because correct final-...