· ai
[Paper] Relu and softplus neural nets as zero-sum turn-based games
We show that the output of a ReLU neural network can be interpreted as the value of a zero-sum, turn-based, stopping game, which we call the ReLU net game. The ...
-
- · ai
[Paper] Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuits
Large language models (LLMs) generate fluent and complex outputs but often fail to recognize their own mistakes and hallucinations. Existing approaches typicall...
- · ai
[Paper] Improving ML Training Data with Gold-Standard Quality Metrics
Hand-tagged training data is essential to many machine learning tasks. However, training data quality control has received little attention in the literature, d...
- · ai
[Paper] Performative Policy Gradient: Optimality in Performative Reinforcement Learning
Post-deployment machine learning algorithms often influence the environments they act in, and thus shift the underlying dynamics that the standard reinforcement...
- · ai
[Paper] Fail Fast, Win Big: Rethinking the Drafting Strategy in Speculative Decoding via Diffusion LLMs
Diffusion Large Language Models (dLLMs) offer fast, parallel token generation, but their standalone use is plagued by an inherent efficiency-quality tradeoff. W...
- · ai
[Paper] Distilling to Hybrid Attention Models via KL-Guided Layer Selection
Distilling pretrained softmax attention Transformers into more efficient hybrid architectures that interleave softmax and linear attention layers is a promising...
- · ai
[Paper] LEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving
Simulators can generate virtually unlimited driving data, yet imitation learning policies in simulation still struggle to achieve robust closed-loop performance...
- · ai
[Paper] Shallow Neural Networks Learn Low-Degree Spherical Polynomials with Learnable Channel Attention
We study the problem of learning a low-degree spherical polynomial of degree ell_0 = Θ(1) ge 1 defined on the unit sphere in RR^d by training an over-parameteri...
- · ai
[Paper] FlashVLM: Text-Guided Visual Token Selection for Large Multimodal Models
Large vision-language models (VLMs) typically process hundreds or thousands of visual tokens per image or video frame, incurring quadratic attention cost and su...
- · ai
[Paper] Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models
Vision-language models (VLM) excel at general understanding yet remain weak at dynamic spatial reasoning (DSR), i.e., reasoning about the evolvement of object g...
- · ai
[Paper] Advancing Multimodal Teacher Sentiment Analysis:The Large-Scale T-MED Dataset & The Effective AAM-TSA Model
Teachers' emotional states are critical in educational scenarios, profoundly impacting teaching efficacy, student engagement, and learning achievements. However...
- · ai
[Paper] Step-DeepResearch Technical Report
As LLMs shift toward autonomous agents, Deep Research has emerged as a pivotal metric. However, existing academic benchmarks like BrowseComp often fail to meet ...