· ai
[Paper] Training AI Co-Scientists Using Rubric Rewards
AI co-scientists are emerging as a tool to assist human researchers in achieving their research goals. A crucial feature of these AI co-scientists is the abilit...
-
- · ai
[Paper] Diffusion Knows Transparency: Repurposing Video Diffusion for Transparent Object Depth and Normal Estimation
Transparent objects remain notoriously hard for perception systems: refraction, reflection and transmission break the assumptions behind stereo, ToF and purely ...
- · ai
[Paper] Eliciting Behaviors in Multi-Turn Conversations
Identifying specific and often complex behaviors from large language models (LLMs) in conversational settings is crucial for their evaluation. Recent work propo...
- · ai
[Paper] Bellman Calibration for V-Learning in Offline Reinforcement Learning
We introduce Iterated Bellman Calibration, a simple, model-agnostic, post-hoc procedure for calibrating off-policy value predictions in infinite-horizon Markov ...
- · ai
[Paper] Fine-Tuning LLMs with Fine-Grained Human Feedback on Text Spans
We present a method and dataset for fine-tuning language models with preference supervision using feedback-driven improvement chains. Given a model response, an...
- · ai
[Paper] PROFASR-BENCH: A Benchmark for Context-Conditioned ASR in High-Stakes Professional Speech
Automatic Speech Recognition (ASR) in professional settings faces challenges that existing benchmarks underplay: dense domain terminology, formal register varia...
- · ai
[Paper] Multilingual Hidden Prompt Injection Attacks on LLM-Based Academic Reviewing
Large language models (LLMs) are increasingly considered for use in high-impact workflows, including academic peer review. However, LLMs are vulnerable to docum...
- · ai
[Paper] Web World Models
Language agents increasingly require persistent worlds in which they can act, remember, and learn. Existing approaches sit at two extremes: conventional web fra...
- · ai
[Paper] End-to-End Test-Time Training for Long Context
We formulate long-context language modeling as a problem in continual learning rather than architecture design. Under this formulation, we only use a standard a...
- · ai
[Paper] Calibrated Multi-Level Quantile Forecasting
We present an online method for guaranteeing calibration of quantile forecasts at multiple quantile levels simultaneously. A sequence of α-level quantile foreca...
- · ai
[Paper] Random Controlled Differential Equations
We introduce a training-efficient framework for time-series learning that combines random features with controlled differential equations (CDEs). In this approa...
- · ai
[Paper] IDT: A Physically Grounded Transformer for Feed-Forward Multi-View Intrinsic Decomposition
Intrinsic image decomposition is fundamental for visual understanding, as RGB images entangle material properties, illumination, and view-dependent effects. Rec...