DWIM: Towards Tool-aware Visual Reasoning via Discrepancy-aware Workflow Generation & Instruct-Masking Tuning
Paper • 2503.19263 • Published • 2
AI & ML interests
None defined yet.
Recent Activity
View all activity
codezakh
authored 7
papers about 21 hours ago
Executable Functional Abstractions: Inferring Generative Programs for Advanced Math Problems
Paper • 2504.09763 • Published • 12
OpenThoughts: Data Recipes for Reasoning Models
Paper • 2506.04178 • Published • 54
One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration
Paper • 2510.12088 • Published • 5
PRInTS: Reward Modeling for Long-Horizon Information Seeking
Paper • 2511.19314 • Published • 8
Cog-DRIFT: Exploration on Adaptively Reformulated Instances Enables Learning from Hard Reasoning Problems
Paper • 2604.04767 • Published • 7
Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind
Paper • 2604.11666 • Published • 3
nick11roberts
submitted a
paper to Daily Papers 10 days ago
Muennighoff
submitted a
paper to Daily Papers 17 days ago
wenwenD
submitted a
paper to Daily Papers about 2 months ago
liangyuch
authored a
paper about 2 months ago
liangyuch
submitted a
paper to Daily Papers about 2 months ago
0xrobertzhang
authored a
paper about 2 months ago
marianna13
published 7
models 3 months ago
mlfoundations-dev/Qwen3-8B_exp-swd-r2egym-standard_glm_4.7_traces_locetash_save-strategy_steps
Updated
mlfoundations-dev/Qwen3-8B_exp_tas_temp_2.0_traces_save-strategy_steps
Updated
mlfoundations-dev/Qwen3-8B_exp_tas_trajectory_minimal_traces_save-strategy_steps
Updated
mlfoundations-dev/Qwen3-8B_exp_tas_temp_0.25_traces_save-strategy_steps
Updated
mlfoundations-dev/Qwen3-8B_exp_tas_summarize_threshold_4096_traces_save-strategy_steps
Updated
mlfoundations-dev/Qwen3-8B_perturbed-docker-exp-taskmaster2-tasks_glm_4.7_traces_locetash_save-strategy_steps
Updated
mlfoundations-dev/Qwen3-8B_exp_tas_temp_0.5_traces_save-strategy_steps
Updated