Unlearning Deceptive Behaviors in LLMs with Contrastive Forget Sets
Research
Research News
New papers, breakthroughs and academic AI research
Learning Where to Steer: Noise-Space Geometry for Efficient Offline Multi-Objective Optimization with Generative Models
Research
How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?
Research
FrontierGS: Progressive View-Space Frontier Expansion for Sparse 3D Gaussian Splatting
Research
Flow Matching under Noisy Latent Structure: Beyond Exact Low-Dimensional Support
Research
Reconstructing the Vocal Tract with Differentiable Acoustic Simulation
Research
What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agents
Research
PivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn Agents
Research
Adaptive Self-Consistency: From Black-Box Sampling to Distribution-Valued Feedback
Research
Who Verifies the Graph? Misspecification Attacks on Causal Action Verification for Language Agents
Research
Unlearnable, or Unmeasured? On the Reliability of Difficulty Labels in RLVR
Research
WorldAuditBench: Interactive 3D World Auditing with Multimodal Agents
Research