Tag: #research297 results
CLI-Gym generates 1,655 CLI tasks via agentic environment inversion from Dockerfiles. It simulates histories to create buggy states and derives tasks with error messages. Fine-tuned LiberCoder boosts Terminal-Bench scores by 21.1%.
C^2ROPE enhances Rotary Position Embedding for 3D Large Multimodal Models by addressing spatial locality loss and long-term attention decay. It introduces spatio-temporal continuous positional embeddings using triplet hybrid indices and Chebyshev Causal Masking. Evaluations show superior performance on 3D scene reasoning and VQA benchmarks.
BNRM introduces Bayesian non-negative reward modeling to combat reward hacking in RLHF. It uses sparse latent factors for disentangled, debiased rewards. Scalable amortized VI enables end-to-end training on LLMs.
Introduces Blockwise Advantage Estimation for GRPO in structured generations, assigning per-objective advantages to avoid interference. Uses Outcome-Conditioned Baseline to estimate advantages without nested rollouts. Competitive on math tasks with uncertainty estimation.
Multi-dimensional zero-shot benchmark evaluates four TSFMs (Chronos, Moirai, TinyTimeMixer) vs. baselines on ERCOT data. Tests context sensitivity, calibration, robustness to shifts like COVID/Winter Storm. Top models hit MASE 0.31; Chronos-2 best calibrated.
EvoCodeBench evaluates LLM-driven coding systems on self-evolution, efficiency, and human-comparable performance across languages. Tracks dynamics like solving time and improvements over iterations. Enables cross-language robustness analysis.
Proposes causal reward shaping from offline data for continuous RL under confounders. Derives tight value bounds via causal Bellman equation for PBRS. Outperforms SAC on benchmarks.
Introduces authenticated workflows as a complete trust layer for enterprise agentic AI, protecting prompts, tools, data, and context. Enforces intent and integrity via cryptography and MAPL policy language. Integrates with nine AI frameworks for deterministic security.
AugVLA-3D integrates depth estimation from RGB inputs via VGGT to enrich 3D features in vision-language-action models. An action assistant module ensures consistency with control tasks. It enhances generalization and robustness in complex 3D robotic environments.
AudioRouter applies RL to teach large audio language models (LALMs) when to use external audio tools, improving fine-grained perception without heavy training. It optimizes a lightweight routing policy while freezing the base model. Achieves big gains on benchmarks with 600x less data than traditional methods.